期刊
IEEE ACCESS
卷 4, 期 -, 页码 3201-3209出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2016.2578638
关键词
Multi-label; classification; clustering; recommendation
资金
- National Natural Science Foundation of China [91546123]
With the explosive development of communication technologies, more customer friendly services have been designed for the next generation of cellular technology, that is, fifth-generation (5G) communication. However, such services require more computing resources and energy. Thus, the development of green and energy-efficient 5G application systems has become an important topic in communications. In this paper, we focus on high-performance multi-label classification methods and their application for medical recommendations in the domain of 5G communication. In machine learning, multi-label classification involves assigning multiple target labels to each query instance. The vast number of labels poses a challenge for maintaining efficiency. Several related approaches have been proposed to meet this challenge. In this paper, we propose two label selection methods for multi-label classification: clustering-based sampling and frequency-based sampling. We apply our proposed multi-label classification methods as an innovative 5G application to predict doctor labels for doctor recommendations. We perform experiments on real-world data sets. The experimental results show that our methods achieve the state-of-the-art performance compared with baselines. In addition, we develop a mobile application of a doctor recommendation system based on our proposed methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据