核K均值聚类改进神经网络垃圾标签检测模型

发布时间：2018-07-21 21:22

【摘要】：为了提高垃圾标签检测精度,提出一种核K均值聚类和改进神经网络相融合的垃圾标签检测模型。首先核K均值聚类算法提抽取垃圾标签的特征向量,然后将特征向量集输入到BP神经网络进行训练,并采用混沌粒子群算法对BP神经网络的参数进行优化,最后建立垃圾标签检测模型,并通过仿真实验对模型性能测试。结果表明,该垃圾标签检测算法模型不仅提高了垃圾标签识别率,训练时间大幅度减少,垃圾标签检测效率得到提高,可以较好满足垃圾标签实时、在线检测要求。
[Abstract]:In order to improve the accuracy of garbage tag detection, a garbage tag detection model based on kernel K-means clustering and improved neural network is proposed. Firstly, the kernel K-means clustering algorithm is used to extract the feature vector of garbage tag, then the eigenvector set is input into BP neural network for training, and chaotic particle swarm optimization algorithm is used to optimize the parameters of BP neural network. Finally, the garbage tag detection model is established, and the performance of the model is tested by simulation experiment. The results show that the algorithm model not only improves the identification rate of garbage tag, but also reduces the training time and improves the efficiency of garbage tag detection. It can meet the requirements of real-time and on-line detection of garbage tag.
【作者单位】：新乡广播电视大学;
【分类号】：TP393.0;TP183

【共引文献】