计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2013年
10期
114-117
,共4页
蛋白质折叠识别%ELM分类优化方法%多类分类
蛋白質摺疊識彆%ELM分類優化方法%多類分類
단백질절첩식별%ELM분류우화방법%다류분류
protein fold recognition%optimization method of ELM for classification%multi-class classification
传统的机器学习方法在处理蛋白质折叠类型识别问题时需要花费大量的时间来调节最佳参数,利用一种新的极限学习机(Extreme Learning Machine,ELM)分类优化方法(Extreme Learning Machine for Classification,ELMC)对蛋白质折叠进行识别,仅需调节很少的参数值就可达到很好的测试精度.与支持向量机(Support Vector Machine,SVM)和推荐相关向量机(Relevance Vector Machine,RVM)相比,ELMC能获得更好的泛化性能,而且在寻找最优解的训练时间比较上,ELMC比SVM平均要快35倍,比RVM要快12倍.
傳統的機器學習方法在處理蛋白質摺疊類型識彆問題時需要花費大量的時間來調節最佳參數,利用一種新的極限學習機(Extreme Learning Machine,ELM)分類優化方法(Extreme Learning Machine for Classification,ELMC)對蛋白質摺疊進行識彆,僅需調節很少的參數值就可達到很好的測試精度.與支持嚮量機(Support Vector Machine,SVM)和推薦相關嚮量機(Relevance Vector Machine,RVM)相比,ELMC能穫得更好的汎化性能,而且在尋找最優解的訓練時間比較上,ELMC比SVM平均要快35倍,比RVM要快12倍.
전통적궤기학습방법재처리단백질절첩류형식별문제시수요화비대량적시간래조절최가삼수,이용일충신적겁한학습궤(Extreme Learning Machine,ELM)분류우화방법(Extreme Learning Machine for Classification,ELMC)대단백질절첩진행식별,부수조절흔소적삼수치취가체도흔호적측시정도.여지지향량궤(Support Vector Machine,SVM)화추천상관향량궤(Relevance Vector Machine,RVM)상비,ELMC능획득경호적범화성능,이차재심조최우해적훈련시간비교상,ELMC비SVM평균요쾌35배,비RVM요쾌12배.
With traditional machine learning methods, one may spends a lot of time adjusting the optimal parameters in tackling the problem of protein fold recognition. A new optimization method of ELM for classification is used to recognize the protein fold, one can only adjusts few parameters to achieve good enough testing accuracy. Compared to SVM and RVM, better general-ization performance can be obtained by ELMC, in the comparison of training time in finding the optimal solution, ELMC is 35 times faster than SVM averagely and is 12 times faster than RVM averagely.
