Advertisement

InsightGAN: Semi-Supervised Feature Learning with Generative Adversarial Network for Drug Abuse Detection

  • Guangzhen Liu
  • Jun Hu
  • An Zhao
  • Mingyu Ding
  • Yuqi Huo
  • Zhiwu Lu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11303)

Abstract

We present a novel generative adversarial network (GAN) model, called InsightGAN, for drug abuse detection. Our model is inspired by two closely related works on machine learning for healthcare applications: (1) drug abuse detection has been solved by machine learning with plentiful data from social media (where face pictures can be easily obtained); (2) facial characteristics have been explored in mental disorder diagnosis (drug addiction is also a mental disorder). In this paper, we adopt deep learning to extract discriminative facial features for drug abuse detection. However, in this application, the face pictures with ground-truth labels are far from sufficient for training a deep learning model. To alleviate the scarcity of labelled data, we thus propose a semi-supervised facial feature learning model based on GAN. Moreover, we also develop a robust algorithm for training our InsightGAN. Experimental results show the promising performance of our InsightGAN.

Keywords

Drug abuse detection Deep learning Social media 

Notes

Acknowledgements

This work was partially supported by National Natural Science Foundation of China (61573363), and the Fundamental Research Funds for the Central Universities and the Research Funds of Renmin University of China (15XNLQ01).

References

  1. 1.
    Aldridge, K., George, I.D., Cole, K.K., et al.: Facial phenotypes in subgroups of prepubertal boys with autism spectrum disorders are correlated with clinical phenotypes. Mol. Autism 2(1), 15 (2011)CrossRefGoogle Scholar
  2. 2.
    Alnajjar, A., Idris, A.M., Multzenberg, M., Mccord, B.: Development of a capillary electrophoresis method for the screening of human urine for multiple drugs of abuse. J. Chromatogr. B 856(1–2), 62–67 (2007)CrossRefGoogle Scholar
  3. 3.
    Austin, J.R., Takahashi, T.N., Duan, Y.: Distinct facial phenotypes in children with autism spectrum disorders and their unaffected siblings. In: International Meeting for Autism Research (2012)Google Scholar
  4. 4.
    Baciu, T., Borrull, F., Aguilar, C., Calull, M.: Recent trends in analytical methods and separation techniques for drugs of abuse in hair. Analytica Chimica Acta 856, 1–26 (2015)Google Scholar
  5. 5.
    Coloma, P.M., Becker, B., Sturkenboom, M.C., van Mulligen, E.M., Kors, J.A.: Evaluating social media networks in medicines safety surveillance: two case studies. Drug Saf. 38(10), 921–30 (2015)CrossRefGoogle Scholar
  6. 6.
    Cone, E.J., Huestis, M.A.: Interpretation of oral fluid tests for drugs of abuse. Ann. New York Acad. Sci. 1098(1), 51–103 (2010)CrossRefGoogle Scholar
  7. 7.
    Dai, Z., Yang, Z., Yang, F., Cohen, W., Salakhutdinov, R.: Good semi-supervised learning that requires a bad GAN. arXiv Preprint arXiv:1705.0978 (2017)
  8. 8.
    Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017)CrossRefGoogle Scholar
  9. 9.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., et al.: Generative adversarial nets. In: NIPS, pp. 2672–2680 (2014)Google Scholar
  10. 10.
    Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87–102. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46487-9_6CrossRefGoogle Scholar
  11. 11.
    Hanson, C.L., Cannon, B., Burton, S., Giraudcarrier, C.: An exploration of social circles and prescription drug abuse through Twitter. J. Med. Int. Res. 15(9), e189 (2013)Google Scholar
  12. 12.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  13. 13.
    Hinton, G.E., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Huestis, M.A., Smith, M.L.: Modern analytical technologies for the detection of drug abuse and doping. Drug Discovery Today Technol. 3(1), 49–57 (2007)CrossRefGoogle Scholar
  15. 15.
    Ingraham, C.: Heroin deaths surpass gun homicides for the first time, CDC data shows. The Washington Post (2016). Accessed 8 Dec 2016Google Scholar
  16. 16.
    Jia, Z., et al.: Tracking the evolution of drug abuse in China, 2003-10: a retrospective, self-controlled study. Addiction 110(S1), 4–10 (2015)CrossRefGoogle Scholar
  17. 17.
    LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521, 436–444 (2015)CrossRefGoogle Scholar
  18. 18.
    Lee, J.G., Jun, S., Cho, Y.W., et al.: Deep learning in medical imaging: general overview. Korean J. Radiol. 18(4), 570–584 (2017)CrossRefGoogle Scholar
  19. 19.
    Long, E., Lin, H., et al.: An artificial intelligence platform for the multihospital collaborative management of congenital cataracts. Nat. Biomed. Eng. 1, 0024 (2017)CrossRefGoogle Scholar
  20. 20.
    Lucey, P., Cohn, J.F., Kanade, T., Saragih, J., Ambadar, Z., Matthews, I.: The extended Cohn-Kanad dataset (CK+): a complete dataset for action unit and emotion-specified expression. In: CVPR Workshops, pp. 94–101 (2010)Google Scholar
  21. 21.
    Odena, A.: Semi-supervised learning with generative adversarial networks. In: ICML 2016 Workshop on Data-Efficient Machine Learning (2016)Google Scholar
  22. 22.
    Peters, F.T., Kraemer, T., Maurer, H.H.: Drug testing in blood: validated negative-ion chemical ionization gas chromatographicc-mass spectrometric assay for determination of amphetamine and methamphetamine enantiomers and its application to toxicology cases. Clin. Chem. 48(9), 1472–1485 (2002)Google Scholar
  23. 23.
    Phan, N., Chun, S.A., Bhole, M., Geller, J.: Enabling real-time drug abuse detection in Tweets. In: ICDE Workshop (2017)Google Scholar
  24. 24.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv Preprint arXiv:1511.06434 (2015)
  25. 25.
    Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NIPS, pp. 2234–2242 (2016)Google Scholar
  26. 26.
    Sarker, A., et al.: Social media mining for toxicovigilance: automatic monitoring of prescription medication abuse from Twitter. Drug Saf. 39(3), 231–240 (2016)CrossRefGoogle Scholar
  27. 27.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: CVPR, pp. 815–823 (2015)Google Scholar
  28. 28.
    Shen, L., Bai, L.: A review on Gabor wavelets for face recognition. Patt. Anal. Appl. 9(2–3), 273–292 (2006)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  30. 30.
    Stolle, M., Sack, P.M., Thomasius, R.: Substance abuse in children and adolescents - early detection and intervention. Dtsch Arztebl 104(28–29), A2061–A2070 (2007)Google Scholar
  31. 31.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: AAAI, pp. 4278–4284 (2017)Google Scholar
  32. 32.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818–2826 (2016)Google Scholar
  33. 33.
    Zhai, G., Ren, F., Zhang, G., Evison, M.: Facial shape analysis based on Euclidean distance matrix analysis. In: International Conference on Biomedical Engineering and Informatics, pp. 1896–1900 (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Guangzhen Liu
    • 1
  • Jun Hu
    • 1
  • An Zhao
    • 1
  • Mingyu Ding
    • 1
  • Yuqi Huo
    • 1
  • Zhiwu Lu
    • 1
  1. 1.Beijing Key Laboratory of Big Data Management and Analysis Methods, School of InformationRenmin University of ChinaBeijingChina

Personalised recommendations