Skip to main content
SpringerLink
Log in

Active inference for dynamic Bayesian networks with an application to tissue engineering

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

In temporal domains, agents need to actively gather information to make more informed decisions about both the present and the future. When such a domain is modeled as a temporal graphical model, what the agent observes can be incorporated into the model by setting the respective random variables as evidence. Motivated by a tissue engineering application where the experimenter needs to decide how early a laboratory experiment can be stopped so that its possible future outcomes can be predicted within an acceptable uncertainty, we first present a dynamic Bayesian network (DBN) model of vascularization in engineered tissues and compare it with both real-world experimental data and agent-based simulations. We then formulate the question of “how early an experiment can be stopped to guarantee an acceptable uncertainty about the final expected outcome” as an active inference problem for DBNs and empirically and analytically evaluate several search algorithms that aim to find the ideal time to stop a tissue engineering laboratory experiment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Akar B, Jiang B, Somo SI, Appel AA, Larson JC, Tichauer KM, Brey EM (2015) Biomaterials with persistent growth factor gradients in vivo accelerate vascularized tissue formation. Biomaterials 72:61–73

  2. Artel A, Mehdizadeh H, Chiu Y-C, Brey EM, Cinar A (2011) An agent-based model for the investigation of neovascularization within porous scaffolds. Tissue Eng Part A 17(17–18):2133–2141

    Article  Google Scholar 

  3. Attenberg J, Melville P, Provost F (2010) A unified approach to active dual supervision for labeling features and examples. In: Proceedings of the european conference on machine learning (ECML), pp 40–55

  4. Bailey AM, Thorne BC, Peirce SM (2007) Multi-cell agent-based simulation of the microvasculature to study the dynamics of circulating inflammatory cell trafficking. J Biomed Eng Soc 35(6):916–936

    Google Scholar 

  5. Bentley K, Gerhardt H, Bates PA (2008) Agent-based simulation of notch-mediated tip cell selection in angiogenic sprout initialisation. J Theor Biol 250(1):25–36

    Article  Google Scholar 

  6. Bianco P, Robey PG (2001) Stem cells in tissue engineering. Nature 414(6859):118–121

    Article  Google Scholar 

  7. Bilgic M (2012) Combining active learning and dynamic dimensionality reduction. In: Proceedings of the SIAM international conference on data mining (SDM)

  8. Bilgic M, Getoor L (2009) Reflect and correct: a misclassification prediction approach to active inference. ACM Trans Knowl Discov Data 3(4):1–32

    Article  Google Scholar 

  9. Bilgic M, Getoor L (2010) Active inference for collective classification. In: Proceedings of the AAAI conference on artificial intelligence (AAAI NECTAR Track), pp 1652–1655

  10. Bilgic M, Getoor L (2011) Value of information lattice: exploiting probabilistic independence for effective feature subset acquisition. J Artif Intell Res (JAIR) 41:69–95

    MATH  Google Scholar 

  11. Bromley J, Jackson NA, Clymer OJ, Giacomello AM, Jensen FV (2005) The use of Hugin to develop Bayesian networks as an aid to integrated water resource planning. Environ Model Softw 20(2):231–242

    Article  Google Scholar 

  12. Byrne DP, Lacroix D, Planell JA, Kelly DJ, Prendergast PJ (2007) Simulation of tissue differentiation in a scaffold as a function of porosity, young’s modulus and dissolution rate: application of mechanobiological models in tissue engineering. Biomaterials 28(36):5544–5554

    Article  Google Scholar 

  13. Chapelle O, Zhang Y (2009) A dynamic Bayesian network click model for web search ranking. In: Proceedings of the international conference on world wide web (WWW), pp 1–10

  14. Chen D, Bilgic M, Getoor L, Jacobs D (2011) Dynamic processing allocation in video. IEEE Trans Pattern Anal Mach Intell 33:2174–2187

    Article  Google Scholar 

  15. Chen D, Bilgic M, Getoor L, Jacobs D, Mihalkova L, Yeh T (2011) Active inference for retrieval in camera networks. In: Proceedings of IEEE workshop on person oriented vision

  16. Chiu Y-C, Cheng M-H, Engel H, Kao S-W, Larson JC, Gupta S, Brey EM (2011) The role of pore size on vascularization and tissue remodeling in PEG hydrogels. Biomaterials 32(26):6045–6051

    Article  Google Scholar 

  17. Chiu Y-C, Kocagoz S, Larson JC, Brey EM (2013) Evaluation of physical and mechanical properties of porous poly (ethylene glycol)-co-(l-lactic acid) hydrogels during degradation. PLoS One 8:4

    Google Scholar 

  18. Dagan I, Engelson SP (1995) Committee-based sampling for training probabilistic classifiers. In: Proceedings of the international conference on machine learning (ICML), pp 150–157

  19. Druck G, Settles B, McCallum A (2009) Active learning by labeling features. In: Proceedings of the conference on empirical methods in natural language processing (EMNLP), pp 81–90

  20. Forbes J, Huang T, Kanazawa K, Russell S (1995) The BATmobile: towards a Bayesian automated taxi. In: Proceedings of the international joint conference on artificial intelligence (IJCAI), pp 1878–1885

  21. Husmeier D (2003) Sensitivity and specificity of inferring genetic regulatory interactions from microarray experiments with dynamic Bayesian networks. Bioinformatics 19(17):2271–2282

    Article  Google Scholar 

  22. Jiang B, Akar B, Waller T, Larson J, Appel A, Brey E (2014) Design of a composite biomaterial system for tissue engineering applications. Acta Biomater 10(3):1177–1186

    Article  Google Scholar 

  23. Jiang B, Waller TM, Larson JC, Appel AA, Brey EM (2013) Fibrin-loaded porous poly(ethylene glycol) hydrogels as scaffold materials for vascularized tissue formation. Tissue Eng Part A 19:224–234

    Article  Google Scholar 

  24. Koller D, Friedman N (2009) Probabilistic graphical models: principles and techniques. The MIT Press, Cambridge

    MATH  Google Scholar 

  25. Komurlu C, Bilgic M (2016) Active inference and dynamic gaussian Bayesian networks for battery optimization in wireless sensor networks. In: Proceedings of AAAI workshop on artificial intelligence for smart grids and smart buildings

  26. Komurlu C, Shao J, Bilgic M (2014) Dynamic Bayesian network modeling of vascularization in engineered tissues. In: Proceedings of the eleventh UAI Bayesian modeling applications workshop

  27. Krause A, Guestrin C (2009) Optimal value of information in graphical models. J Artif Intell Res 35:557–591

    MathSciNet  MATH  Google Scholar 

  28. Langer R, Vacanti J (1993) Tissue engineering. Science 260(5110):920–926

    Article  Google Scholar 

  29. Lewis DD, Gale WA (1994) A sequential algorithm for training text classifiers. In: Proceedings of the ACM SIGIR conference on research and development in information retrieval’, pp 3–12

  30. Li W-J, Tuli R, Okafor C, Derfoul A, Danielson KG, Hall DJ, Tuan RS (2005) A three-dimensional nanofibrous scaffold for cartilage tissue engineering using human mesenchymal stem cells. Biomaterials 26(6):599–609

    Article  Google Scholar 

  31. Mao J, Giannobile W, Helms J, Hollister S, Krebsbach P, Longaker M, Shi S (2006) Craniofacial tissue engineering by stem cells. J Dent Res 85(11):966–979

    Article  Google Scholar 

  32. Mehdizadeh H, Artel A, Brey EM, Cinar A (2011) Multi-agent systems for biomedical simulation: modeling vascularization of porous scaffolds. In: Proceedings of the international conference on agents in principle, agents in practice, pp 113–128

  33. Mehdizadeh H, Sumo S, Bayrak ES, Brey EM, Cinar A (2013) Three-dimensional modeling of angiogenesis in porous biomaterial scaffolds. Biomaterials 34(12):2875–2887

    Article  Google Scholar 

  34. Melville P, Sindhwani V (2009) Active dual supervision: reducing the cost of annotating examples and features. In: Proceedings of the NAACL HLT workshop on active learning for natural language processing, pp 49–57

  35. Min Z, Conzen SD (2005) A new dynamic Bayesian network (DBN) approach for identifying gene regulatory networks from time course microarray data. Bioinformatics 21(1):71–79

    Article  Google Scholar 

  36. Pavlović V, Rehg JM, Cham T-J, Murphy KP (1999) A dynamic Bayesian network approach to figure tracking using learned dynamic models, In: The proceedings of the seventh IEEE international conference on computer vision, 1999, vol 1, pp 94–101

  37. Perrin BE, Ralaivola L, Mazurie A, Bottani S, Mallet J, d’Alche Buc F (2003) Gene networks inference using dynamic Bayesian networks. Bioinformatics 19(suppl 2):ii138–ii148

    Article  Google Scholar 

  38. Raghavan H, Allan J (2007) An interactive algorithm for asking and incorporating feature feedback into support vector machines. In: Proceedings of the ACM SIGIR conference on research and development in information retrieval, pp 79–86

  39. Ramirez-Loaiza ME, Culotta A, Bilgic M (2013) Towards anytime active learning: interrupting experts to reduce annotation costs. In: Proceedings of the IDEA workshop at ACM SIGKDD conference on knowledge discovery and data mining

  40. Ramirez-Loaiza ME, Culotta A, Bilgic M (2014) Anytime active learning. In: Proceedings of the AAAI conference on artificial intelligence

  41. Roy N, McCallum A (2001) Toward optimal active learning through sampling estimation of error reduction. In: Proceedings of the international conference on machine learning (ICML), pp 441–448

  42. Settles B (2012) Active learning. Synth Lect Artif Intell MachLearn 6(1):1–114

  43. Settles B, Craven M (2008) An analysis of active learning strategies for sequence labeling tasks. In: Proceedings of the conference on empirical methods in natural language processing, pp 1070–1079

  44. Seung HS, Opper M, Sompolinsky H (1992) Query by committee. In: Proceedings of the conference on learning theory (COLT), pp 287–294

  45. Sharma M, Bilgic M (2013) Most-surely vs. least-surely uncertain. In: Proceedings of the IEEE international conference on data mining (ICDM)

  46. Sharma M, Bilgic M (2016) Evidence-based uncertainty sampling for active learning. Data Min Knowl Disc. doi:10.1007/s10618-016-0460-3

  47. Sharma M, Zhuang D, Bilgic M (2015) Active learning with rationales for text classification. In: Proceedings of the North American chapter of the association for computational linguistics—human language technologies

  48. Small K, Wallace BC, Brodley CE, Trikalinos TA (2011) The constrained weight space svm: learning with ranked features. In: Proceedings of the international conference on machine learning (ICML), pp 865–872

  49. Somo SI, Akar B, Bayrak ES, Larson JC, Appel AA, Mehdizadeh H, Cinar A, Brey EM (2015) Pore interconnectivity influences growth factor-mediated vascularization in sphere-templated hydrogels. Tissue Eng Part C Methods 21(8):773–785

    Article  Google Scholar 

  50. Uusitalo L (2007) Advantages and challenges of Bayesian networks in environmental modelling. Ecol Modell 3(203):312–318

    Article  Google Scholar 

  51. Yang S, Leong K-F, Du Z, Chua C-K (2004) The design of scaffolds for use in tissue engineering. Part I. Traditional factors. Tissue Eng 7:679–689

    Article  Google Scholar 

  52. Zaidan OF, Eisner J, Piatko CD (2007) Using annotator rationales to improve machine learning for text categorization. In: Proceedings of the conference of the North American chapter of the association for computational linguistics—human language technologies, pp 260–267

  53. Zweig G, Russell S (1998) Speech recognition with dynamic Bayesian networks. In: Proceedings of the national conference on artificial intelligence/innovative applications of artificial intelligence, pp 173–180

Download references

Acknowledgments

This material is based upon work supported by the National Science Foundation under Grant No. IIS-1125412.

Author information

Authors and Affiliations

  1. Department of Computer Science, Illinois Institute of Technology, Chicago, IL, 60616, USA

    Caner Komurlu, Jinjian Shao & Mustafa Bilgic

  2. Department of Biomedical Engineering, Illinois Institute of Technology, Chicago, IL, USA

    Banu Akar & Eric M. Brey

  3. Department of Chemical and Biological Engineering, Illinois Institute of Technology, Chicago, IL, USA

    Elif S. Bayrak & Ali Cinar

Authors
  1. Caner Komurlu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jinjian Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Banu Akar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Elif S. Bayrak
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Eric M. Brey
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ali Cinar
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Mustafa Bilgic
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mustafa Bilgic.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Komurlu, C., Shao, J., Akar, B. et al. Active inference for dynamic Bayesian networks with an application to tissue engineering. Knowl Inf Syst 50, 917–943 (2017). https://doi.org/10.1007/s10115-016-0963-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-016-0963-7

Keywords

Search

Navigation