吉林大学学报(工学版) ›› 2025, Vol. 55 ›› Issue (8): 2746-2752.doi: 10.13229/j.cnki.jdxbgxb.20240772

• 计算机科学与技术 • 上一篇    

软件定义物联网中多源异构数据混合属性特征检测

张连连1,2(),郭伟2,刘锋1()   

  1. 1.北京航空航天大学 电子信息工程学院,北京 100191
    2.河北建筑工程学院 电气工程学院,河北 张家口 075000
  • 收稿日期:2024-07-12 出版日期:2025-08-01 发布日期:2025-11-14
  • 通讯作者: 刘锋 E-mail:lianlianzhang@buaa.com.cn;liufuil@sina.com
  • 作者简介:张连连(1984-),女,副教授.研究方向:信息网络.E-mail:lianlianzhang@buaa.com.cn
  • 基金资助:
    国家自然科学基金项目(62302231)

Detection of mixed attribute features of multi-source heterogeneous data in software defined IoT

Lian-lian ZHANG1,2(),Wei GUO2,Feng LIU1()   

  1. 1.School of Electronics and Information Engineering,Beihang University,Beijing 100191,China
    2.School of Electrical Engineering,Hebei University of Architecture,Zhangjiakou 075000,China
  • Received:2024-07-12 Online:2025-08-01 Published:2025-11-14
  • Contact: Feng LIU E-mail:lianlianzhang@buaa.com.cn;liufuil@sina.com

摘要:

软件定义物联网中多源异构数据来源于不同设备,具有不同的格式、结构和质量,增加了特征检测的复杂性。因此,本文提出软件定义物联网中多源异构数据混合属性特征检测方法。利用联合卡尔曼滤波算法对软件定义物联网中的多源异构数据实施融合处理,完成异构数据的初步整合,结合证据分类算法,将具有相同混合属性的网络数据划分至同一数据集中,实现多源异构数据的分类。基于多源数据的逆相似特性,引入边缘算子计算方法对分类后的数据属性特征展开拆分,结合支持向量机将混合属性特征转化为线性可分问题,实现多源异构数据属性特征的精准检测。实验表明,本文方法的协方差计算结果始终在0.15以下,对不同属性特征之间的区分较明显,且检测概率在0.8以上。该方法能实现软件定义物联网中多源异构数据混合属性的精准划分。

关键词: 联合卡尔曼滤波算法, 软件定义物联网, 证据分类算法, 边缘算子, 支持向量机

Abstract:

In the software defined Internet of Things (IoT), multi-source heterogeneous data comes from different devices and has different formats, structures, and qualities, which increases the complexity of feature detection. Therefore, a mixed attribute feature detection method for multi-source heterogeneous data in software defined IoT is proposed. Using the joint Kalman filtering algorithm to fuse multi-source heterogeneous data in the software defined Internet of Things, completing the initial integration of heterogeneous data. Combined with evidence classification algorithms, network data with the same mixed attributes are divided into the same dataset to achieve classification of multi-source heterogeneous data. Based on the inverse similarity characteristics of multi-source data, an edge operator calculation method is introduced to split the classified data attribute features, and combined with support vector machines, accurate detection of multi-source heterogeneous data attribute features is achieved. The experiment shows that the covariance calculation results of the proposed method are always below 0.15, and the distinction between different attribute features is more obvious, with a detection probability of over 0.8. This method can achieve precise partitioning of mixed attributes of multi-source heterogeneous data in software defined IoT.

Key words: joint Kalman filtering algorithm, software defined Internet of things, evidence classification algorithm, edge operator, support vector machine

中图分类号: 

  • TP311.13

图1

数据可视化检测环境"

表1

数据融合效果对比"

数据集

编号

协方差值
本文方法时间序列算法加权融合算法
10.150.420.73
20.130.360.32
30.140.510.27
40.120.370.56
50.130.440.47
60.150.450.36
70.140.560.58
80.130.600.66

图2

混合属性特征划分效果"

图3

不同方法的检测效果对比"

[1] 覃伟荣, 劳燕玲. 基于3D关联规则深度学习的异构遥感数据检测[J]. 计算机仿真, 2023, 40(9): 482-486.
Qin Wei-rong, Lao Yan-ling. Detection of heterogeneous remote sensing data based on deep learning of 3D association rules[J].Computer Simulation, 2023,40(9): 482-486.
[2] 洪德华, 刘翠玲, 赵林燕, 等. 基于多域特征分析与选择的电力数据识别方法[J]. 水电能源科学, 2023, 41(9): 211-215.
Hong De-hua, Liu Cui-ling, Zhao Lin-yan, et al. Power data identification method based on multi-domain feature analysis and selection[J]. Water Resources and Power, 2023, 41(9): 211-215.
[3] Puerto S C, Larrañaga P, Bielza C. Feature subset selection in data-stream environments using asymmetric hidden Markov models and novelty detection[J]. Neurocomputing, 2023, 554: 126641.
[4] 刘晋成, 唐伦, 陈前斌. 基于数据特征的多传感器融合实时目标检测[J]. 计算机应用研究, 2023, 40(11):3456-3461.
Liu Jin-cheng, Tang Lun, Chen Qian-bin. Multi-sensor fusion real-time target detection based on data characteristics[J]. Application Research of Computers, 2023, 40(11): 3456-3461.
[5] 顾伟, 行鸿彦, 侯天浩. 基于网络流量时空特征和自适应加权系数的异常流量检测方法[J]. 电子与信息学报, 2024, 46(6): 1-8.
Gu Wei, Xing Hong-yan, Hou Tian-hao. Anomalous traffic detection method based on spatiotemporal characteristics of network traffic and adaptive weighting coefficients[J]. Journal of Electronics & Information Technology, 2024, 46(6): 1-8.
[6] 史鼎元, 王晏晟, 郑鹏飞, 等. 面向企业数据孤岛的联邦排序学习[J]. 软件学报, 2021, 32(3): 669-688.
Shi Ding-yuan, Wang Yan-sheng, Zheng Peng-fei, et al. Cross-silo federated learning-to-rank[J]. Journal of Software, 2021, 32(3): 669-688.
[7] 夏伟, 蔡文婷, 刘阳, 等. 基于联合卡尔曼滤波的配电网多源异构数据融合[J]. 电力系统保护与控制,2022, 50(10): 180-187.
Xia Wei, Cai Wen-ting, Liu Yang, et al. Multi-source heterogeneous data fusion of a distribution network based on a joint Kalman filter[J]. Power System Protection and Control, 2022, 50(10): 180-187.
[8] 王楠, 周喜超, 彭勇, 等. 基于证据KNN分类器的蓄电池一致性诊断[J]. 太阳能学报, 2022, 43(4): 13-19.
Wang Nan, Zhou Xi-chao, Peng Yong, et al. Battery consistency diagnosis based on evidential KNN classifierr[J].Acta Energiae Solaris Sinica, 2022, 43(4): 13-19.
[9] 宋丽萍, 陈德峰, 田甜, 等. 基于雷达测距和测速的GEO目标实时关联算法[J]. 北京航空航天大学学报, 2023, 49(8): 2167-2175.
Song Li-ping, Chen De-feng, Tian Tian, et al. A real-time correlation algorithm for GEO targets based on radar ranging and velocity measurement[J]. Journal of Beihang University, 2023, 49(8): 2167-2175.
[10] 殷炜宏, 王若愚, 段倩倩, 等. 基于时态边缘算子的时间序列自主分段表示法[J]. 计算机工程与科学,2021, 43(6): 1104-1111.
Yin Wei-hong, Wang Ruo-yu, Duan Qian-qian, et al. An autonomous segmental representation of time series based on temporal edge operator[J]. Computer Engineering & Science, 2021, 43(6): 1104-1111.
[11] 杨建新, 兰小平, 冯亚东, 等. 基于改进樽海鞘群和最小二乘支持向量机算法的新型弹药质量评估方法[J]. 兵工学报, 2022, 43(5): 1012-1022.
Yang Jian-xin, Lan Xiao-ping, Feng Ya-dong, et al. An ammunition quality evaluation method based on least squares support vector machine[J]. Acta Armamentarii, 2022, 43(5): 1012-1022.
[12] 陈越, 俞耀文. 基于代理拉格朗日松弛的电-氢耦合网络优化调度[J]. 控制工程, 2023, 30(12): 2280-2287.
Chen Yue, Yu Yao-wen. Optimal scheduling of electricity-hydrogen coupling network based on surrogate lagrangian relaxation[J]. Control Engineering of China, 2023, 30(12): 2280-2287.
[1] 邹红波,李奇隆. 基于改进北方苍鹰优化算法的激光焊缝图像分类[J]. 吉林大学学报(工学版), 2025, 55(4): 1426-1435.
[2] 关亮亮,田国红. 基于动力学分析的汽车减震器示功图故障检测算法[J]. 吉林大学学报(工学版), 2024, 54(5): 1221-1226.
[3] 高海龙,徐一博,刘坤,李春阳,卢晓煜. 基于多源数据融合的高速公路路网短时交通流参数实时预测[J]. 吉林大学学报(工学版), 2024, 54(1): 155-161.
[4] 田野,李楠楠,刘君巍,姜生元,王储,张伟伟. 基于支持向量机的模拟月壤临界尺度颗粒切削负载识别[J]. 吉林大学学报(工学版), 2023, 53(7): 2143-2151.
[5] 龙恩深,班光泽. 基于小波包信包提取的空调制冷压缩机怠速噪声诊断算法[J]. 吉林大学学报(工学版), 2023, 53(7): 1929-1934.
[6] 李岩,张久鹏,陈子璇,黄果敬,王培. 基于PCA-PSO-SVM的沥青路面使用性能评价[J]. 吉林大学学报(工学版), 2023, 53(6): 1729-1735.
[7] 吴剑,许斌. 基于CEEMDAN理论的堆积层滑坡位移区间预测模型及仿真[J]. 吉林大学学报(工学版), 2023, 53(2): 562-568.
[8] 宋世军,樊敏. 基于谱聚类的多维数据集异常数据检测方法[J]. 吉林大学学报(工学版), 2023, 53(10): 2917-2922.
[9] 郭世杰,张学炜,张楠,乔冠,唐术锋. 机床主轴热关键点选择与典型转速热误差预测[J]. 吉林大学学报(工学版), 2023, 53(1): 72-81.
[10] 王奎洋,何仁. 基于支持向量机的制动意图识别方法[J]. 吉林大学学报(工学版), 2022, 52(8): 1770-1776.
[11] 罗巍,卢博,陈菲,马腾. 基于PSO-SVM及时序环节的数控刀架故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(2): 392-399.
[12] 院老虎,连冬杉,张亮,刘义. 基于密集连接卷积网络和支持向量机的飞行器机械部件故障诊断[J]. 吉林大学学报(工学版), 2021, 51(5): 1635-1641.
[13] 侯春萍,赵春月,王致芃,田海瑞. 基于有效异常样本构造的视频异常检测算法[J]. 吉林大学学报(工学版), 2021, 51(5): 1823-1829.
[14] 王康,姚猛,李立犇,李建桥,邓湘金,邹猛,薛龙. 基于月面表取采样触月压痕的月壤力学状态分析[J]. 吉林大学学报(工学版), 2021, 51(3): 1146-1152.
[15] 李雄飞,王婧,张小利,范铁虎. 基于SVM和窗口梯度的多焦距图像融合方法[J]. 吉林大学学报(工学版), 2020, 50(1): 227-236.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!