- 截稿日期延期至 2021年4月20日
Biography: Dr. Fang Hu received the Ph.D. degree in Complex Network from School of Computer, Central China Normal University, Wuhan, China. Dr. Hu worked at the University of West Florida as a postdoctoral researcher in the department of Mathematics and Statistics. She is currently an Associate Professor with the College of Information Engineering, Hubei University of Chinese Medicine, Wuhan, China. She has published over 30 papers in SCI, EI journals, etc. She is the guest editor or reviewer for SCI journals. Her main research interests include complex networks, machine learning, optimization algorithms, and data modeling in various research fields.
Topic: On Herb Compatibility Rule of Insomnia Based on Machine Learning Approaches
Abstract: The herb compatibility rule of insomnia is studied using some machine learning approaches. The insomnia data set with 807 samples is extracted from the real-world Electronic Medical Records (EMRs). After cleaning and selecting the theme data referring to the prescriptions and their herbs, the herb network analysis model is constructed using complex network. Each herb node in network is trained to obtain the herb embeddings using the Skip-Gram model. After acquiring the digital vocabulary of herbs, the similarity among any two herb embeddings is calculated, and these herb embeddings are divided into seven communities using the Spectral Clustering (SC) algorithm. The experimental results shed light on that the methodologies can objectively and effectively discover the relationships among herbs and reveal the herb compatibility for clinical treatment research of insomnia.