Skip to main content
Springer Nature Link
Log in

Generating knowledge for the identification of device failure causes and the prediction of the times-to-failure in u-Healthcare environments

  • Original Article
  • Published:
Personal and Ubiquitous Computing Aims and scope Submit manuscript

Abstract

The healthcare industry depends on a large number of medical devices to perform many of its functions, so a considerable amount of effort is spent to deal with failures occurred in medical devices. This paper proposes a method that generates knowledge used to identify the causes of medical device failures and to predict the times-to-failure (i.e., a period during which a medical device operates without failure). To generate knowledge for failure cause identification, morphemes of the failure data in the existing database are analyzed and similar failures (symptoms and causes) are grouped based on the similarity of symptoms. To generate knowledge for the prediction of the times-to-failure, the Weibull distribution parameters are estimated based on a device’s previous failure dates. The experiment results show that the proposed method has 69 % accuracy in identifying the cause of failure and 83 % accuracy in predicting the times-to-failure. The proposed method enables medical device users to quickly identify the cause of failure when their devices have problems, thereby reducing the cost of failure. With the predicted time to failure, it is possible to have devices (or device parts) ready just in time for replacement. This leads to decreased inventory costs.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
€32.70 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (France)

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

Notes

  1. Data published by the Ministry of Health and Welfare, South Korea.

References

  1. Da Costa CA, Ydamin AC, Geyer CFR (2008) Toward a general software infrastructure for ubiquitous computing. IEEE Pervasive Comput 7(1):64–73

    Article  Google Scholar 

  2. Jung HS, Baek JK, Jeong CS, Lee YW, Hong PD (2007) Unified ubiquitous middleware for U-City. Convergence information technology, 2007. International Conference, pp 2374–2379

  3. Kwon PJ, Kim H, Kim UM (2009) A study on the web-based intelligent self-diagnosis medical system. Adv Eng Softw 40(6):402–406

    Article  MATH  Google Scholar 

  4. Lee JI (2009) Home automation system based on ubiquitous. J Korea Acad Indus Cooper Soc 10(11):3039–3042

    Article  Google Scholar 

  5. Watson RT, Pitt LF, Berthon P, Zinkhan GM (2002) U-commerce: expanding the universe of marketing. J Acad Mark Sci 30(4):333–347

    Article  Google Scholar 

  6. Lee YH, Han DM, Park HK, Lee JD, Koo YW (2005) A demand analysis and market prospect on a portable internet service. Proc Korean Soc Internet Inform Conf 6(1):349–352

    Google Scholar 

  7. Kim HC, Kang JM (2008) Status and prospects of technology for ubiquitous healthcare. Commun Korean Inst Inform Sci Eng 26(1):38–45

    Article  Google Scholar 

  8. Angeli C, Chatzinikolaou A (2004) On-line fault detection techniques for technical systems: a survery. Int J Comput Sci Appl I(1):12–30

    Google Scholar 

  9. Xiong L, Tan Q (2011) A configurable approach to toleration of soft errors via partial software protection. J Converg 2(1):31–38

    MathSciNet  Google Scholar 

  10. Wallace DR, Kuhn DR (2001) Failure modes in medical device software: an analysis of 15 years of recall data. Int J Reliab Qual Saf Eng 8:351–372

    Article  Google Scholar 

  11. Ryu DW (2009) A method for generating rule-based fault diagnosis knowledge on smart home environment. J Korea Acad Indus Cooper Soc 10(10):2741–2749

    Article  Google Scholar 

  12. Lee DG, Kim JW, Lee HS (2008) A case study on determining doors maintenance intervals through running fault data analysis for metro EMU. J Korean Soc Railway 11(3):240–247

    Google Scholar 

  13. Choi JM, Yang SH, Hwang YH, Son IS, On YS, Kim YJ (2010) Failure data analysis of J79 engine transfer gearbox for aircraft maintenance planning. Trans Korean Soc Mech Eng A 34(6):781–787

    Article  Google Scholar 

  14. Lee T, Yu F, Lin Y, Kong X, Yu Y (2011) Trusted computing dynamic attestation using a static analysis based behaviour model. J Converg 2(1):61–68

    Google Scholar 

  15. Sal DD, Casany MP, Pey JL (2010) Cooperative cache analysis for distributed search engines. Int J Inform Technol Commun Converg 1(1):41–65

    Article  Google Scholar 

  16. Lee SJ, Kim TW, Lee KH (1999) Estimation of required time period in terms of expected residual failure data rate based on the Weibull distribution. The Fall Conference of Korea Institute of Communication Science

  17. Baeza-Yates R, Ribeiro-Neto B (1999) Modern information retrieval. Addison-Wesley, Reading

    Google Scholar 

  18. Cavnar WB, Trenkle JM (1994) N-gram-based text categorization. In: Proceedings of SDAIR-94, pp 161–175

  19. Cho HY, Choi SP, Choi JH (2001) A study on the development of a practical morphological analysis system based on word analysis. J Korean Soc Inf Manag 18(2):105–124

    MathSciNet  Google Scholar 

  20. Shim KS, Yang JH (2004) High speed Korean morphological analysis based on adjacency condition check. J KISS Softw Appl 31(1):89–99

    MathSciNet  Google Scholar 

  21. Klyuev V, Oleshchuk V (2011) Semantic retrieval: an approach to representing, searching and summarising text documents. Int J Inform Technol Commun Converg 1(2):221–234

    Article  Google Scholar 

  22. Kim HS, Park HC (1998) Statistics for division of commerce. Hyung-Seul Publishers, Seoul

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Information Communication and Broadcasting Engineering, Halla University, Wonju, Korea

    Dong Woo Ryu

  2. School of Computer Science and Engineering, Chung-Ang University, Seoul, Korea

    Kyung Jin Kang & Sang Oh Park

  3. Division of Computer Engineering, Mokwon University, Taejon, Korea

    Sang Soo Yeo

Authors
  1. Dong Woo Ryu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kyung Jin Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sang Soo Yeo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sang Oh Park
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sang Oh Park.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ryu, D.W., Kang, K.J., Yeo, S.S. et al. Generating knowledge for the identification of device failure causes and the prediction of the times-to-failure in u-Healthcare environments. Pers Ubiquit Comput 17, 1383–1394 (2013). https://doi.org/10.1007/s00779-012-0573-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00779-012-0573-7

Keywords

Search

Navigation