Research article Special Issues

Deep sparse transfer learning for remote smart tongue diagnosis

  • Received: 24 November 2020 Accepted: 21 December 2020 Published: 12 January 2021
  • People are exploring new ideas based on artificial intelligent infrastructures for immediate processing, in which the main obstacles of widely-deploying deep methods are the huge volume of neural network and the lack of training data. To meet the high computing and low latency requirements in modeling remote smart tongue diagnosis with edge computing, an efficient and compact deep neural network design is necessary, while overcoming the vast challenge on modeling its intrinsic diagnosis patterns with the lack of clinical data. To address this challenge, a deep transfer learning model is proposed for the effective tongue diagnosis, based on the proposed similar-sparse domain adaptation (SSDA) scheme. Concretely, a transfer strategy of similar data is introduced to efficiently transfer necessary knowledge, overcoming the insufficiency of clinical tongue images. Then, to generate simplified structure, the network is pruned with transferability remained in domain adaptation. Finally, a compact model combined with two sparse networks is designed to match limited edge device. Extensive experiments are conducted on the real clinical dataset. The proposed model can use fewer training data samples and parameters to produce competitive results with less power and memory consumptions, making it possible to widely run smart tongue diagnosis on low-performance infrastructures.

    Citation: Xu Zhang, Wei Huang, Jing Gao, Dapeng Wang, Changchuan Bai, Zhikui Chen. Deep sparse transfer learning for remote smart tongue diagnosis[J]. Mathematical Biosciences and Engineering, 2021, 18(2): 1169-1186. doi: 10.3934/mbe.2021063

    Related Papers:

  • People are exploring new ideas based on artificial intelligent infrastructures for immediate processing, in which the main obstacles of widely-deploying deep methods are the huge volume of neural network and the lack of training data. To meet the high computing and low latency requirements in modeling remote smart tongue diagnosis with edge computing, an efficient and compact deep neural network design is necessary, while overcoming the vast challenge on modeling its intrinsic diagnosis patterns with the lack of clinical data. To address this challenge, a deep transfer learning model is proposed for the effective tongue diagnosis, based on the proposed similar-sparse domain adaptation (SSDA) scheme. Concretely, a transfer strategy of similar data is introduced to efficiently transfer necessary knowledge, overcoming the insufficiency of clinical tongue images. Then, to generate simplified structure, the network is pruned with transferability remained in domain adaptation. Finally, a compact model combined with two sparse networks is designed to match limited edge device. Extensive experiments are conducted on the real clinical dataset. The proposed model can use fewer training data samples and parameters to produce competitive results with less power and memory consumptions, making it possible to widely run smart tongue diagnosis on low-performance infrastructures.


    加载中


    [1] Z. Ning, P. Dong, X. Wang, X. Hu, L. Guo, B. Hu, et al., Mobile edge computing enabled 5G health monitoring for internet of medical things: A decentralized game theoretic approach, IEEE J. Sel. Areas Commun., (2020), 1–16.
    [2] D. C. Mainenti, Big data and traditional chinese medicine (TCM): What's state of the art?, in 2019 IEEE International Conference on Big Data (Big Data), 2019, 1417–1422.
    [3] Q. Jiang, X. Yang, X. Sun, An aided diagnosis model of sub-health based on rough set and fuzzy mathematics: A case of TCM, J. Intell. Fuzzy Syst., 32 (2017), 4135–4143. doi: 10.3233/JIFS-15958
    [4] F. Cui, Deployment and integration of smart sensors with iot devices detecting fire disasters in huge forest environment, Comput. Commun., 150 (2020), 818–827. doi: 10.1016/j.comcom.2019.11.051
    [5] P. H. O. Santos, G. L. Soares, T. M. Machado-Coelho, B. A. G. de Oliveira, P. Y. Ekel, F. M. F. Ferreira, et al., Multi-objective genetic algorithm implemented on a STM32F microcontroller, in 2018 IEEE Congress on Evolutionary Computation (CEC), 2018, 1–7.
    [6] Z. Ning, P. Dong, X. Wang, X. Hu, J. Liu, L. Guo, et al., Partial computation offloading and adaptive task scheduling for 5G-enabled vehicular networks, IEEE Trans. Mob. Comput., (2020).
    [7] Y. Huang, X. Ma, X. Fan, J. Liu, W. Gong, When deep learning meets edge computing, in 2017 IEEE 25th international conference on network protocols (ICNP), 2017, 1–2.
    [8] Z. Ning, K. Zhang, X. Wang, L. Guo, X. Hu, J. Huang, et al., Intelligent edge computing in internet of vehicles: a joint computation offloading and caching solution, IEEE Trans. Intell. Transp. Syst., (2020), 1–14.
    [9] S. Vicente, J. Carreira, L. Agapito, J. Batista, Reconstructing pascal voc, in Proceedings of the IEEE conference on computer vision and pattern recognition, (2014), 41–48.
    [10] Y. Zhang, B. D. Davison, Impact of imagenet model selection on domain adaptation, in Proceedings of the IEEE Winter Conference on Applications of Computer Vision Workshops, (2020), 173–182.
    [11] S. M. Xie, N. Jean, M. Burke, D. B. Lobell, S. Ermon, Transfer learning from deep features for remote sensing and poverty mapping, in Proceedings of the AAAI Conference on Artificial Intelligence, 30 (2016).
    [12] R. Xu, G. Li, J. Yang, L. Lin, Larger norm more transferable: An adaptive feature norm approach for unsupervised domain adaptation, in Proceedings of the IEEE International Conference on Computer Vision, (2019), 1426–1435.
    [13] F. N. Iandola, M. W. Moskewicz, K. Ashraf, S. Han, W. J. Dally, K. Keutzer, SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size, preprint, arXiv: 1602.07360.
    [14] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, et al., Mobilenets: Efficient convolutional neural networks for mobile vision applications, preprint, arXiv: 1704.04861.
    [15] J. Frankle, M. Carbin, The lottery ticket hypothesis: Finding sparse, trainable neural networks, preprint, arXiv: 1803.03635.
    [16] G. Csurka, A comprehensive survey on domain adaptation for visual applications, in Domain adaptation in computer vision applications, Springer, Cham, (2017), 1–35.
    [17] M. Wang, W. Deng, Deep visual domain adaptation: A survey, Neurocomputing, 312 (2018), 135–153. doi: 10.1016/j.neucom.2018.05.083
    [18] X. Huang, Y. Rao, H. Xie, T. Wong, F. L. Wang, Cross-domain sentiment classification via topic-related TrAdaBoost, in Proceedings of the AAAI Conference on Artificial Intelligence, 31 (2017).
    [19] C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, C. Liu, A survey on deep transfer learning, in International conference on artificial neural networks, Springer, Cham, (2018), 270–279.
    [20] H. Chang, J. Han, C. Zhong, A. Snijders, J. Mao, Unsupervised transfer learning via multi-scale convolutional sparse coding for biomedical applications, IEEE Trans. Pattern Anal. Mech. Intell., 40 (2017), 1182–1194.
    [21] E. Tzeng, J. Hoffman, N. Zhang, K. Saenko, T. Darrell, Deep domain confusion: Maximizing for domain invariance, preprint, arXiv: 1412.3474.
    [22] M. Long, Y. Cao, J. Wang, M. I. Jordan, Learning transferable features with deep adaptation networks, in International conference on machine learning, PMLR, (2015), 97–105.
    [23] B. Sun, K. Saenko, Deep coral: Correlation alignment for deep domain adaptation, in European conference on computer vision, Springer, Cham, (2016), 443–450.
    [24] L. Zhang, X. Li, J. Lai, L. Zhang, Bioinformatics databases for network pharmacology research of traditional chinese medicine: A systematic review, in 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, (2017), 1400–1404.
    [25] Y. Ye, B. Xu, L. Ma, J. Zhu, H. Shi, X. Cai, Research on treatment and medication rule of insomnia treated by TCM based on data mining, in 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, (2019), 2503–2508.
    [26] K. Tago, H. Wang, Q. Jin, Classification of TCM pulse diagnoses based on pulse and periodic features from personal health data, in 2019 IEEE Global Communications Conference (GLOBECOM), IEEE, (2019), 1–6.
    [27] J. Wei, J. Wang, Y. Zhu, J. Sun, H. Xu, M. Li, Traditional chinese medicine pharmacovigilance in signal detection: decision tree-based data classification, BMC Med. Inf. Decis. Making, 18 (2018), 19. doi: 10.1186/s12911-018-0599-5
    [28] C. Wu, T. Chen, Y. Hsieh, H. Tsao, A hybrid rule mining approach for cardiovascular disease detection in traditional chinese medicine, J. Intell. Fuzzy Syst., 36 (2019), 861–870. doi: 10.3233/JIFS-169864
    [29] Y. Li, H. Ye, An analysis and research of type-2 diabetes TCM records based on text mining, in 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), (2018), 1872–1875.
    [30] J. Yang, Y. Wen, G. Zhao, J. Duan, Research on association rules of breast cancer and TCM : Syndrome based on data mining, in 2019 IEEE Symposium Series on Computational Intelligence (SSCI), (2019), 2788–2792.
    [31] X. Li, Q. Shao, J. Wang, Classification of tongue coating using gabor and tamura features on unbalanced data set, in 2013 IEEE International Conference on Bioinformatics and Biomedicine, (2013), 108–109.
    [32] J. Ding, G. Cao, D. Meng, Classification of tongue images based on doublet SVM, in 2016 International Symposium on System and Software Reliability (ISSSR), (2016), 77–81.
    [33] Z. Qi, L. P. Tu, J. B. Chen, X. J. Hu, J. T. Xu, Z. F. Zhang, The classification of tongue colors with standardized acquisition and icc profile correction in traditional Chinese medicine, BioMed Res. Int., 2016 (2016).
    [34] T. C. Lee, L. C. Lo, F. C. Wu, Traditional chinese medicine for metabolic syndrome via TCM pattern differentiation: tongue diagnosis for predictor, Evidence-Based Complementary Altern. Med., 2016 (2016).
    [35] W. Liu, C. Zhou, Z. Li, Z. Hu, Patch-driven tongue image segmentation using sparse representation, IEEE Access, 8 (2020), 41372–41383. doi: 10.1109/ACCESS.2020.2976826
    [36] W. Jiao, X. Hu, L. Tu, C. Zhou, Z. Qi, Z. Luo, et al., Tongue color clustering and visual application based on 2D information, Int. J. Comput. Assist. Radiol. Surg., 15 (2020), 203–212. doi: 10.1007/s11548-019-02076-z
    [37] W. Tang, Y. Gao, L. Liu, T. Xia, L. He, S. Zhang, et al., An automatic recognition of tooth-marked tongue based on tongue region detection and tongue landmark detection via deep learning, IEEE Access, 8 (2020), 153470–153478. doi: 10.1109/ACCESS.2020.3017725
    [38] S. Sadasivan, T. T. Sivakumar, A. P. Joseph, G. C. Zacharias, M. S. Nair, Tongue print identification using deep CNN for forensic analysis, J. Intell. Fuzzy Syst., 38 (2020), 6415–6422. doi: 10.3233/JIFS-179722
    [39] L. Li, Z. Luo, M. Zhang, Y. Cai, C. Li, S. Li, An iterative transfer learning framework for cross-domain tongue segmentation, Concurr. Comput. Pract., 32 (2020).
    [40] H. Yang, J. Zhang, H. Dong, N. Inkawhich, A. Gardner, A. Touchet, et al., DVERGE: diversifying vulnerabilities for enhanced robust generation of ensembles, preprint, arXiv: 2009.14720.
  • Reader Comments
  • © 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(3961) PDF downloads(242) Cited by(0)

Article outline

Figures and Tables

Figures(7)  /  Tables(1)

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog