基于BP学习的P2P网络信任度评价模型优化
|
摘要
由于P2P营销网络中随机性和模型固态性因素的存在,导致信任度评价误差较大。提出一种基于自适应BP神经网络加权学习的P2P网络商家信任度评价模型。采用网络爬虫和关联规则挖掘方式实现P2P网络信任度评价的关联大数据信息采样,以卖家商业信誉、网络平台可靠性和网络环境安全性一级指标,将原始网络信任度特征量输入到BP神经网络中,设置信任度评价模型的模糊约束参量,采用极限自适应学习算法得到信任度评价全局最优解,挖掘P2P网络商家信任度的关联规则特征量,实现对网络信任度的优化评价。仿真结果表明,采用该方法进行P2P网络商家信任度评价的准确性较高,置信度水平较好,对信任度关联数据挖掘的准确性较好。
Due to the existence of randomness and solid model in P2P marketing network,the evaluation error of trust degree is large.This paper presents a P2P network merchant trust evaluation model based on adaptive BP neural network weighted learning.Using crawler and association rules mining to realize the associated big data information sampling of P2P network trust evaluation,the first grade index of seller′s business reputation,network platform reliability and network environment security is adopted.The original network trust characteristic is input into the BP neural network,the fuzzy constraint parameter of the trust evaluation model is set,and the global optimal solution of trust evaluation is obtained by using the limit adaptive learning algorithm.The association rule characteristic quantity of P2P network merchant trust is excavated to realize the optimization evaluation of network trust degree.The simulation results show that this method is more accurate and reliable in evaluating the trust degree of P2P network merchants,and the accuracy of association data mining of trust degree is better.
Due to the existence of randomness and solid model in P2P marketing network,the evaluation error of trust degree is large.This paper presents a P2P network merchant trust evaluation model based on adaptive BP neural network weighted learning.Using crawler and association rules mining to realize the associated big data information sampling of P2P network trust evaluation,the first grade index of seller′s business reputation,network platform reliability and network environment security is adopted.The original network trust characteristic is input into the BP neural network,the fuzzy constraint parameter of the trust evaluation model is set,and the global optimal solution of trust evaluation is obtained by using the limit adaptive learning algorithm.The association rule characteristic quantity of P2P network merchant trust is excavated to realize the optimization evaluation of network trust degree.The simulation results show that this method is more accurate and reliable in evaluating the trust degree of P2P network merchants,and the accuracy of association data mining of trust degree is better.
引文
[1]吴恒亮.Web挖掘在电子商务推荐系统中的应用研究[J].中国商贸,2010(4):78-79.
[2]吴九雄.Web挖掘在电子商务中的应用研究[J].信息系统工程,2010(1):72-74.
[3]蔡念,黄威威,谢伟,叶等.基于互补自适应噪声的集合经验模式分解算法[J].电子与信息学报,2015,37(10):2383-2389.
[4]ZHENG J,CHENG J,YANG Y.Partly ensemble empirical mode decomposition:An improved noiseassisted method for eliminating mode mixing[J].Signal Processing,2014(96):362-374.
[5]甘早斌,曾灿,李开,等.电子商务下的信任网络构造与优化[J].计算机学报,2012,35(1):27-36.
[6]SHEN W C,CHEN Y H,WU A Y A.Lowcomplexity sinusoidal-assisted EMD(SAEMD)algorithms for solving mode-mixing problems in HHT[J].Digital Signal Processing,2014(24):170-186.
[7]BADRINARAYANAN V,KENDALL A,CIPOLLAR.SegNet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[8]徐乃凡,王俊芳,郭建立,等.面向边缘云高效能的移动终端计算迁移方法[J].电子测量技术,2018,41(20):1-6.
[9]薛雪,王建平,孙伟.微电网数据通信无线传感器网络性能的跨层控制方法研究[J].电子测量与仪器学报,2018,32(10):15-25.
[10]戴洪德,李娟,景博,等.基于HP滤波与非线性维纳过程的退化建模与失效分布研究[J].仪器仪表学报,2018,39(8):63-71.
[11]WEI X S,LUO J H,WU J.Selective convolutional descriptor aggregation for fine-grained image retrieval[J].IEEE Transactions on Image Processing,2017,26(6):2868-2881.
[12]RAZAVIAN A S,SULLIVAN J,CARLSSON S.Visual instance retrieval with deep convolutional networks[J].ITE Transactions on Media Technology and Applications,2016,4(3):251-258.
[13]毛宇星,郭云飞,王志明,等.基于资源区域聚集度的虚拟网映射算法[J].电子与信息学报,2015,37(10):2405-2410.
[14]沈士根,马绚,蒋华,等.基于演化博弈论的WSNs信任决策模型与动力学分析[J].控制与决策,2012,27(8):1133-1138.
[15]吴旭.基于增强稳定组模型的移动P2P网络信任评估方法[J].计算机学报,2014,37(10):2118-2127.
[2]吴九雄.Web挖掘在电子商务中的应用研究[J].信息系统工程,2010(1):72-74.
[3]蔡念,黄威威,谢伟,叶等.基于互补自适应噪声的集合经验模式分解算法[J].电子与信息学报,2015,37(10):2383-2389.
[4]ZHENG J,CHENG J,YANG Y.Partly ensemble empirical mode decomposition:An improved noiseassisted method for eliminating mode mixing[J].Signal Processing,2014(96):362-374.
[5]甘早斌,曾灿,李开,等.电子商务下的信任网络构造与优化[J].计算机学报,2012,35(1):27-36.
[6]SHEN W C,CHEN Y H,WU A Y A.Lowcomplexity sinusoidal-assisted EMD(SAEMD)algorithms for solving mode-mixing problems in HHT[J].Digital Signal Processing,2014(24):170-186.
[7]BADRINARAYANAN V,KENDALL A,CIPOLLAR.SegNet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[8]徐乃凡,王俊芳,郭建立,等.面向边缘云高效能的移动终端计算迁移方法[J].电子测量技术,2018,41(20):1-6.
[9]薛雪,王建平,孙伟.微电网数据通信无线传感器网络性能的跨层控制方法研究[J].电子测量与仪器学报,2018,32(10):15-25.
[10]戴洪德,李娟,景博,等.基于HP滤波与非线性维纳过程的退化建模与失效分布研究[J].仪器仪表学报,2018,39(8):63-71.
[11]WEI X S,LUO J H,WU J.Selective convolutional descriptor aggregation for fine-grained image retrieval[J].IEEE Transactions on Image Processing,2017,26(6):2868-2881.
[12]RAZAVIAN A S,SULLIVAN J,CARLSSON S.Visual instance retrieval with deep convolutional networks[J].ITE Transactions on Media Technology and Applications,2016,4(3):251-258.
[13]毛宇星,郭云飞,王志明,等.基于资源区域聚集度的虚拟网映射算法[J].电子与信息学报,2015,37(10):2405-2410.
[14]沈士根,马绚,蒋华,等.基于演化博弈论的WSNs信任决策模型与动力学分析[J].控制与决策,2012,27(8):1133-1138.
[15]吴旭.基于增强稳定组模型的移动P2P网络信任评估方法[J].计算机学报,2014,37(10):2118-2127.