- P-ISSN 1225-0163
- E-ISSN 2288-8985
- 권한신청
- P-ISSN1225-0163
- E-ISSN2288-8985
- SCOPUS, ESCI, KCI
논문 상세
Home > 논문 상세
Application and evaluation of machine-learning model for fire accelerant classification from GC-MS data of fire residue
분석과학 / Analytical Science and Technology, (P)1225-0163; (E)2288-8985
2021, v.34 no.5, pp.231-239
https://doi.org/10.5806/AST.2021.34.5.231
(Daejeon District Office, National Forensic Service)
(Daejeon District Office, National Forensic Service)
(Daejeon District Office, National Forensic Service)
(Daejeon District Office, National Forensic Service)
(Daegu District Office, National Forensic Service)
(Daejeon District Office, National Forensic Service)
(Daejeon District Office, National Forensic Service)
(Daejeon District Office, National Forensic Service)
(Daegu District Office, National Forensic Service)
Chihyun,
P.
,
Wooyong,
P.
,
Sookyung,
J.
,
Sumin,
L.
,
&
Joon-Bae,
L.
(2021). . 분석과학, 34(5), 231-239, https://doi.org/10.5806/AST.2021.34.5.231
- 다운로드 수
- 조회수
Abstract
Detection of fire accelerants from fire residues is critical to determine whether the case was arson or accidental fire. However, to develop a standardized model for determining the presence or absence of fire accelerants was not easy because of high temperature which cause disappearance or combustion of components of fire accelerants. In this study, logistic regression, random forest, and support vector machine models were trained and evaluated from a total of 728 GC-MS analysis data obtained from actual fire residues. Mean classification accuracies of the three models were 63 %, 81 %, and 84 %, respectively, and in particular, mean AU-PR values of the three models were evaluated as 0.68, 0.86, and 0.86, respectively, showing fine performances of random forest and support vector machine models.
- keywords
- GC-MS, machine learning, random forest, support vector machine
참고문헌
1
1. R. M. Smith, Anal. Chem., 54(13), 1399A-1409A (1982).
2
2. A. Hamins, M. Bundy and S. E. Dillon, J. Fire Prot. Eng., 15(4), 265-285 (2005).
3
3. A. D. Pert, M. G. Baron and J. W. Birkett, J. Forensic Sci., 51(5), 1033-1049 (2006).
4
4. S. T. Teng, A. D. Williams and K. Urdal, J. High. Resolut. Chromatogr., 17(6), 469-475 (1994).
5
5. R. O. Keto, J. Forensic Sci., 40(3), 412-423 (1995).
6
6. C. H. Wu, C. L. Chen, C. T. Huang, M. R. Lee and C. M. Huang, Anal. Lett., 37(7), 1373-1384 (2004).
7
7. J. N. Eisenberg and T. E. McKone, Environ. Sci. Technol., 32(21), 3396-3404 (1998).
8
8. E. Akkaş, L. Akin, H. E. Çubukçu and H. Artuner, Comput. Geosci., 80, 38-48 (2015).
9
9. M. G. Yıldız, T. Davran-Candan, M. E. Günay and R. Yıldırım, J. CO2 Util., 31, 27-42 (2019).
10
10. D. C. Mann, J. Forensic Sci., 32(3), 616-628 (1987).
11
11. J. S. Cramer, The Origins of Logistic Regression, http://dx.doi.org/10.2139/ssrn.360300, Assessed 25 Jan 2003.
12
12. L. Breiman, M. Lear., 45(1), 5-32 (2001).
13
13. C. Cortes and V. Vapnik, M. Lear., 20(3), 273-297 (1995).
14
14. A. Luque, A. Carrasco, A. Martín and A. de las Heras, Pattern Recognit., 91, 216-231 (2019).
15
15. H. He, Y. Bai, E. A. Garcia and S. Li, ‘ADASYN:Adaptive synthetic sampling approach for imbalanced learning’, IEEE, 2008.
권호 내 다른 논문
- Liquid chromatography-tandem mass spectrometric analysis of oleracone D and its application to pharmacokinetic study in mice
- Development of primary reference gas mixtures of 18 volatile organic compounds in hazardous air pollutants (5 nmol/mol level) and their analytical methods
- Method development and validation of spectrophotometric and RP-HPLC methods for simultaneous estimation of spironolactone and furosemide in bulk and combined tablet dosage forms
- Effectiveness of interference filter for photoluminescence observations: comparison with absorption filters
- Application and evaluation of machine-learning model for fire accelerant classification from GC-MS data of fire residue
- more
추천 논문
학술지 홈페이지 이용 환경은 크롬 브라우저 사용을 권장합니다.