Automatic Classification of Bloodstain Patterns Caused by Gunshot and Blunt Impact at Various Distances Liu, Yu Attinger, Daniel De Brabanter, Kris Attinger, Daniel
dc.contributor.department Center for Statistics and Applications in Forensic Evidence
dc.contributor.department Computer Science
dc.contributor.department Mechanical Engineering
dc.contributor.department Statistics 2020-04-14T21:29:14.000 2020-06-30T01:58:16Z 2020-06-30T01:58:16Z Tue Jan 01 00:00:00 UTC 2019 2020-01-16
dc.description.abstract <p>The forensics discipline of bloodstain pattern analysis plays an important role in crime scene analysis and reconstruction. One reconstruction question is whether the blood has been spattered via gunshot or blunt impact such as beating or stabbing. This paper proposes an automated framework to classify bloodstain spatter patterns generated under controlled conditions into either gunshot or blunt impact classes. Classification is performed using machine learning. The study is performed with 94 blood spatter patterns which are available as public data sets, designs a set of features with possible relevance to classification, and uses the random forests method to rank the most useful features and perform classification. The study shows that classification accuracy decreases with the increasing distance between the target surface collecting the stains and the blood source. Based on the data set used in this study, the model achieves 99% accuracy in classifying spatter patterns at distances of 30 cm, 93% accuracy at distances of 60 cm, and 86% accuracy at distances of 120 cm. Results with 10 additional backspatter patterns also show that the presence of muzzle gases can reduce classification accuracy.</p>
dc.description.comments <p>This is a manuscript of an article published as Liu, Yu, Daniel Attinger, and Kris De Brabanter. "Automatic Classification of Bloodstain Patterns Caused by Gunshot and Blunt Impact at Various Distances." <em>Journal of Forensic Sciences</em> (2019). Posted with permission of CSAFE.</p>
dc.format.mimetype application/pdf
dc.identifier archive/
dc.identifier.articleid 1027
dc.identifier.contextkey 17326553
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath csafe_pubs/32
dc.language.iso en
dc.source.bitstream archive/|||Fri Jan 14 23:34:44 UTC 2022
dc.source.uri 10.1111/1556-4029.14262
dc.subject.disciplines Forensic Science and Technology
dc.subject.keywords forensic science
dc.subject.keywords bloodstain pattern analysis
dc.subject.keywords classification
dc.subject.keywords impact spatters
dc.subject.keywords gunshot spatters
dc.subject.keywords spatter pattern
dc.subject.keywords machine learning
dc.subject.keywords image analysis
dc.subject.keywords random forests
dc.subject.keywords feature engineering
dc.title Automatic Classification of Bloodstain Patterns Caused by Gunshot and Blunt Impact at Various Distances
dc.type article
dc.type.genre article
dspace.entity.type Publication
relation.isAuthorOfPublication 584f53d6-fea9-47aa-a192-697ef4c972b7
relation.isOrgUnitOfPublication d8a3c72b-850f-40f6-87c4-8812547080c7
relation.isOrgUnitOfPublication f7be4eb9-d1d0-4081-859b-b15cee251456
relation.isOrgUnitOfPublication 6d38ab0f-8cc2-4ad3-90b1-67a60c5a6f59
relation.isOrgUnitOfPublication 264904d9-9e66-4169-8e11-034e537ddbca
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
1.47 MB
Adobe Portable Document Format