Multi-label classification methods for green computing and application for mobile medical recommendations

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.