Parallel algorithms of random forests for classifying very large datasets

The random forests algorithm proposed by Breiman is an ensemble-based approach with very high accuracy. The learning and classification tasks of a set of decision trees take a lot of time, make it intractable when dealing with ve ry large datasets. There is a need to scale up the random forests a...

תיאור מלא

שמור ב:
מידע ביבליוגרפי
Những tác giả chính: Do, Thanh Nghi, Pham, Nguyen Khang
פורמט: Bài viết
שפה:English
יצא לאור: Trường Đại học Đà Lạt 2014
נושאים:
גישה מקוונת:https://scholar.dlu.edu.vn/thuvienso/handle/DLU123456789/37523
תגים: הוספת תג
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
Thư viện lưu trữ: Thư viện Trường Đại học Đà Lạt
תיאור
סיכום:The random forests algorithm proposed by Breiman is an ensemble-based approach with very high accuracy. The learning and classification tasks of a set of decision trees take a lot of time, make it intractable when dealing with ve ry large datasets. There is a need to scale up the random forests algorithm to handle massive datasets. We propose parallel algorithms of random forests to take into account the benefits of Grids computing. These algorithms improve training and classification time compared with the original ones. The experimental results on large datasets including Forest cover type, KDD Cup 1999, Connect-4 from the UCI data repository showed that the training and classification time of parallel algorithms are significantly reduced.