摘要
针对产品销售时序具有正态高斯分布、幅值较大、奇异点等混合噪音,设计一种鲁棒损失函数,并采用小波核函数,由此得到一种新的小波ν-支持向量机,即鲁棒小波ν-支持向量机(Robust wavelet ν-support vector machine,RWν-SVM).它可以有效地压制销售时序的多种噪音和奇异点,具有很强的鲁棒性,而且它比标准小波ν-支持向量机(Wν-SVM)具有更简洁的对偶优化问题.最后进行了汽车销售预测的实例分析,结果表明基于RWν-SVM的预测模型是有效可行的.
Aiming at the normal Gaussian distributional noise, greater breadth noise and oddity point noise of product sales series and combing a designed robust loss function with wavelet kernel function, we propose a new wavelet v-support vector machine, named as robust wavelet v-support vector machine （RWv-SVM）. The RWv-SVM, which has a stronger robustness and simpler dual optimization problem than standard waveletsupport vector machine （Wv-SVM）, can inhibit some types of noise and disturbing oddity point noise of product sales series effectively. Finally, the RWv-SVM is applied to the forecasts of car sales, and the results show that the forecasting model based on the proposed RWv-SVM is effective and feasible.
出处
《自动化学报》
EI
CSCD
北大核心
2009年第7期1027-1032,共6页
Acta Automatica Sinica
基金
家高技术研究发展计划(863计划)(2007AA04Z112)
国家自然科学基金(50875046
60574062)资助~~
关键词
支持向量机
小波核函数
鲁棒损失函数
预测
Support vector machine （SVM）, wavelet kernel function, robust loss function, forecasting
