计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (9): 217-219.

• 工程与应用 • 上一篇    下一篇

改进的RBFNN在运动员竞技状态预测中的应用

张 乐1,魏振钢1,姚晓晓1,杨红云2   

  1. 1.中国海洋大学 计算机系,山东 青岛 266100
    2.青岛酒店管理学院,山东 青岛 266100
  • 收稿日期:2007-07-12 修回日期:2007-09-17 出版日期:2008-03-21 发布日期:2008-03-21
  • 通讯作者: 张 乐

Application of RBF neural network based on mixture clustering in forecasting of athlete’s sports state

ZHANG Le1,WEI Zhen-gang1,YAO Xiao-xiao1,YANG Hong-yun2   

  1. 1.Department of Computer Science and Technology,Ocean University of China,Qingdao,Shandong 266100,China
    2.Qingdao Hismile College,Qingdao,Shandong 266100,China
  • Received:2007-07-12 Revised:2007-09-17 Online:2008-03-21 Published:2008-03-21
  • Contact: ZHANG Le

摘要: 提出了一种改进的径向基函数(RBF)神经网络,该神经网络以模糊系统模型为基础。首先利用减法聚类算法确定径向基函数的中心数,然后通过模糊C均值聚类算法优化基函数中心与宽度,最后依据样本数据的聚类结果设计RBF神经网络并进行训练。将该神经网络应用于网球队运动员的竞技状态的预测。仿真结果表明:该算法先进有效、具有较高的精度,用其建立的模型具有较强的实用性。

关键词: 径向基神经网络(RBFNN), 减聚类算法, 模糊C均值算法, 竞技状态, 预测

Abstract: This paper presents an improved RBF neural network which based on fuzzy system model.The first determine the centers’ number of RBF using subtractive clustering method,the second optimize the position of the centers and centers’ width in RBF according to fuzzy C-mean algorithm,the last design and train the RBF neural network depending on the result of samples clustering.The neural network is used to forecast the sports state of the tennis athletes.The result of this algorithm is effective and has higher precision,and this model can be available to the domain.

Key words: radial basis function neural network, subtractive clustering, fuzzy C-mean algorithm, sports state, forecasting