Interpretable Tongue Constitution Recognition via Reshaped Wavelet Attention
-
Published:2024-02-14
Issue:1
Volume:17
Page:
-
ISSN:1875-6883
-
Container-title:International Journal of Computational Intelligence Systems
-
language:en
-
Short-container-title:Int J Comput Intell Syst
Author:
Wen Guihua, Liang Haozan, Li HuihuiORCID, Wen Pengcheng, Chen Rui, Li Cheng
Abstract
AbstractCurrently deep neural networks have been used to perform the tongue constitution recognition, but they are still challenged, failing to extract nice multi-scale and multi-level features. This paper proposes a novel interpretable tongue constitution recognition method based on the reshaped wavelet attention. It separates multi-scale features through discrete wavelet transform and then uses the attention mechanism to weight them. Subsequently, these features are reshaped to the high-dimensional space where the association knowledge of multi-level features are mined and hierarchized so as to fuse them efficiently. Finally, both are integrated into the framework of convolution neural network to generate the more accurate tongue image attributes, by which the tongue constitution recognition is performed. The proposed method not only obtains the higher performance with small cost, but also nicely interprets them. Experimental results show that the proposed method is effective, efficient, and interpretable.
Funder
National Natural Science Foundation of China Department of Education of Guangdong Province Guangdong Province Introduction of Innovative R &D Team Basic and Applied Basic Research Foundation of Guangdong Province
Publisher
Springer Science and Business Media LLC
Reference75 articles.
1. Xu, Y., Wen, G., Yang, P., Hu, Y., Luo, M., Wang, C., Hall, W.: Dynamic task-coupling learning for physical sign-based auxiliary disease diagnosis. IEEE J. Biomed. Health Inform. (2021) 2. Mihui, L., Shuming, M., Yubao, L., et al. A study of traditional chinese medicine body constitution associated with overweight, obesity, and underweight. Evid-Based Complement. Alternative Med. 2017:1-8 (2017). https://doi.org/10.1155/2017/7361896 3. Mohammadturusn, N., Xu, Y., Xu, F., Zhang, Y., Tang, Z., Liu, W.: Association study of diabetes mellitus and body constitution of traditional Chinese medicine. Tradit. Med. Mod. Med. 2(1), 1–6 (2019) 4. Dai, Y., Wang, G., Dai, J., Geman, O.: A multimodal deep architecture for traditional Chinese medicine diagnosis. Concurr. Comput. Pract. Exp. 32(19) (2020) 5. Liang, X., Wang, Q., Jiang, Z., et al.: Clinical research linking Traditional Chinese Medicine constitution types with diseases: a literature review of 1639 observational studies. J. Tradit. Chin. Med. 40(4), 690–702 (2020)
|
|