一种基于领域知识的特征提取算法
A feature extraction algorithm based on domain knowledge
云南民族大学学报:自然科学版,2017,26(3):252-257

宋园园 SYY

摘要


特征抽取是网络舆情分析中最重要的环节之一,优秀的特征抽取算法能够极大的提高舆情分析的效率和准确率.对旅游网络舆情进行分析和监管,能够及时发现云南旅游中的突发事件,可提供给相关部门以便迅速采取正确的应对方式,对云南的旅游业发展有很大的帮助,分析了传统特征抽取算法正确率低下、运行效率不高等方面的不足,将领域本体知识应用在旅游网络舆情分析的特征抽取算法之中,建立旅游网络舆情领域本体,根据领域本体优化特征抽取计算特征词权重,经过多次大数据量试验验证,优化后的方法显著提高了特征抽取的正确率和运行效率,证明基于领域知识的特征抽取的正确率和运行效率得到很大的提升. Intensity inhomogeneity exists widely in medical images, and it is often a great challenge to accurately segment images with intensity inhomogeneity. This paper presents an active contour model based on Gaussian distributions, and combines it with the bias field model in order to overcome the influence of intensity inhomogeneity on image segmentation. The level-set function is introduced and the algorithm is implemented according to the variation principle. Finally, the proposed level-set method and the classical algorithm are compared. The results show that the proposed algorithm achieves good results in both synthetic and real image segmentation and has a stronger robustness.

参考



全文: PDF      下载: 088      浏览: 083


counter for myspace
云南民族大学学报(自然科学版) 1991—2016 Copyright
地址:云南省昆明市一二.一大街134号 邮编:650031 全国邮发代号:64-47
电话:0871-65132114 传真:0871-65137493 Email:ynmzxyxb@163.com