MapReduce-based adaptive random forest algorithm for multi-label classification

作     者：Wu, Qinghua Wang, Haihui Yan, Xuesong Liu, Xiaobo 

作者机构：Wuhan Inst Technol Fac Comp Sci & Engn Wuhan 430205 Hubei Peoples R China China Univ Geosci Sch Comp Sci Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Hubei Peoples R China China Univ Geosci Sch Automat Wuhan 430074 Hubei Peoples R China 

出 版 物：《NEURAL COMPUTING & APPLICATIONS》 (神经网络计算与应用)

年 卷 期：2019年第31卷第12期

页      面：8239-8252页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China, NSFC, (61673354) China University of Geosciences, Beijing, CUGB, (Wuhan) Huazhong University of Science and Technology, HUST State Key Lab of Digital Manufacturing Equipment and Technology, (DMETKF2018020) Fundamental Research Funds of China West Normal University 

主　　题：Multi-label classification Random forest algorithm Hadoop MapReduce 

摘      要：Due to the complexity of data characteristics, multi-label learning in data mining has been proposed by scholars to solve the problem of information knowledge in the era of big data. In the era of big data, the complexity of the data structures makes it impossible for traditional single-label learning methods to meet the needs of technological development. Moreover, the importance of multi-label learning is gradually becoming evident. The random forest (RF) algorithm is regarded as one of the best classification algorithms. In this study, the traditional decision tree algorithm was improved, and the traditional RF method was converted into an adaptive RF (ARF) method for multi-label classification. By experiments, the effectiveness of the proposed method was verified. The RF method may not be able to classify massive data in a short time, but Hadoop, which was by Apache, is suitable for data-intensive tasks. On this basis, we modified the MapReduce programming mode to make it suitable for the proposed ARF method. This method was implemented on the cloud platform, and the time effectiveness of the parallel model was verified by experiments.