DOI QR코드

DOI QR Code

다중 클래스 SVM을 이용한 스마트폰 중독 자가진단 시스템

Self-diagnostic system for smartphone addiction using multiclass SVM

  • 피수영 (대구가톨릭대학교 교양교육원)
  • Pi, Su Young (Institute of Liberal Education, Catholic University of Daegu)
  • 투고 : 2012.10.26
  • 심사 : 2012.12.03
  • 발행 : 2013.01.31

초록

무선으로 응용 프로그램을 다운받아 실행하고 수많은 응용 프로그램들을 통신 접속이 없어도 실행이 가능하다는 점으로 인해 스마트폰 중독이 인터넷 중독보다 심각한 상태이지만 아직까지 스마트폰 중독과 관련된 연구가 부족한 상태이다. 한국정보화진흥원에서 개발한 스마트폰 중독 검사 척도인 S-척도는 문항수가 많아 응답자들이 진단 자체를 회피할 수도 있으며 인구통계학적 변인도 고려하지 않은 상태에서 체크한 문항들에 대한 총점만으로 중독여부를 진단하므로 정확하게 진단하는데 어려움이 있다. 따라서 본 논문에서는 인구통계학적 변인을 포함한 여러 문항들을 추가한 자료들을 대상으로 먼저 스마트폰 중독에 영향을 미치는 중요한 요인들을 추출해 보았다. 추출한 축소문항을 대상으로 데이터마이닝기법 중 하나인 신경망을 이용하여 분류를 하였다. 신경망 학습알고리즘 중에서 BP학습 알고리즘과 다중 SVM을 이용하여 학습을 시켜 비교, 분석 해 본 결과 다중 SVM의 학습율이 조금 더 높게 나타났다. 본 논문에서 제안한 다중 SVM을 이용하여 학습을 한 자가진단 시스템을 이용하면 자료들의 급격한 변화에 대해 뛰어난 적응성을 가지므로 빠른 시간 내에 자신의 중독여부를 정확하게 자가진단 할 수 있다.

Smartphone addiction has become more serious than internet addiction since people can download and run numerous applications with smartphones even without internet connection. However, smartphone addiction is not sufficiently dealt with in current studies. The S-scale method developed by Korea National Information Society Agency involves so many questions that respondents are likely to avoid the diagnosis itself. Moreover, since S-scale is determined by the total score of responded items without taking into account of demographic variables, it is difficult to get an accurate result. Therefore, in this paper, we have extracted important factors from all data, which affect smartphone addiction, including demographic variables. Then we classified the selected items with a neural network. The result of a comparative analysis with backpropagation learning algorithm and multiclass support vector machine shows that learning rate is slightly higher in multiclass SVM. Since multiclass SVM suggested in this paper is highly adaptable to rapid changes of data, we expect that it will lead to a more accurate self-diagnosis of smartphone addiction.

키워드

참고문헌

  1. Bharat, A. and Barin, N. (1997). Performance evaluation of neural network decision models. Journal of Management Information Systems, 14, 201-230. https://doi.org/10.1080/07421222.1997.11518171
  2. Cheng, J., Yang, S. and Lu, S. (2007). Virus detection and alert for smartphones. Proceedings of the Fifth International Conference on Mobile System, 258-271.
  3. Gjorgii, M., Dejan, G. and Ivan, C. (2009). A multi-class SVM classifier utilizing binary detection tree. Informetica, 33, 233-241.
  4. Hwang, H. S. and Sohn, S. H. (2011). Exploring factors affecting smartphone addiction-characteristics of users and functional attributes. Korean Journal of Broadcasting and Telecommunication Studies, 25, 277-313.
  5. Choi, H. S., Lee, H. K. and Ha, J. (2012). The influence of smartphone addiction on mental health, campus life and personal relations. Journal of the Korean Data & Information Science Society, 23, 1005-1015. https://doi.org/10.7465/jkdi.2012.23.5.1005
  6. Ko, J. P. (2005). Solving multi-class problem using support vector machines. Journal of Korean Institute of Information Scientists and Engineers, 12, 1260-1270.
  7. Kwon, D. S. and Kim, J. H. (2011). An empirical study applying the self-determination factors to flow and satisfaction of smartphone. Journal of the Society for e-Business Studies, 16, 197-214. https://doi.org/10.7838/jsebs.2011.16.4.197
  8. Lee, Y. I. (2010). A study on the smart-phone TAM and satisfaction of college students. Journal of Korea Research Academy of Distribution and Management, 13, 93-101. https://doi.org/10.17961/jdmr.13.5.201012.93
  9. Mercer, J. (1909). Functions of positive and negative type and their connection with the theory of integral equations. Philosophical Transactions of the Royal Society A, 415-446.
  10. National Information Society Agency. (2012). Diagnosing smartphone addiction scale, Korean Internet Addiction Center, Seoul.
  11. Park, J. Y. and Leem, C. H. (2003). Support vector learning for abnormality detection problems. Journal of Korean Institute of Intelligent Systems, 13, 266-274. https://doi.org/10.5391/JKIIS.2003.13.3.266
  12. Pi, S. Y., Park, H. J. and Ryu, K. H. (2011). An analysis of satisfaction index on computer education of university using kernal machine. Journal of the Korean Data & Information Science Society, 22, 921-929.
  13. Rho, M. J. and Kim, J. H. (2010). An exploratory study on smart-phone and service convergence. Journal of the Society for e-Business Studies, 15, 59-77.

피인용 문헌

  1. Modelling smartphone addiction: The role of smartphone usage, self-regulation, general self-efficacy and cyberloafing in university students vol.63, 2016, https://doi.org/10.1016/j.chb.2016.05.091
  2. Comparison of data mining methods with daily lens data vol.24, pp.6, 2013, https://doi.org/10.7465/jkdi.2013.24.6.1341