The Similar Sparse Domain Adaptation Illustrated by the case of TCM Tongue Inspection

More attention is paid to personal health accompanying by the development of society and the change of lifestyle. Not limited in disease, the sub-health is bedeviling humanity more generally. An increasing number of people go in quest of Traditional Chinese Medicine (TCM) for life quality, since TCM achieves the significant and curative effectiveness in recuperating certain sub-health conditions. However, the lack of clinical data poses a vast challenge on the emerging deeplearning-based methods in modeling TCM diagnosis. In this paper, a Similar Sparse Domain Adaptation (SSDA) method is proposed in modeling the tongue inspection, which is one of the four diagnostic methods and plays important roles in TCM primary diagnosis. First, a similar domain adaptation is introduced to transfer necessary knowledge efficiently and overcome insufficient data. Then, inspired by the Lottery Ticket hypothesis, the network is pruned to generate sparse subnet using in adaptation. Finally, the model with two combined sparse network is designed. Extensive experiments are conducted on the real clinical data set collected in Dalian, China. Proposed model uses fewer training data samples and parameters, while consuming less power and memory, which make it easier to store and run on low-power hardware systems for widely promoting.