Discrimination of human and animal bloodstains using hyperspectral imaging

Subtitle: Specim IQ (Specim, Spectral Imaging Ltd., Oulu, Finland)

Metadata

Additional title	Subtitle: Specim IQ (Specim, Spectral Imaging Ltd., Oulu, Finland)
Person(s) who is (are) responsible for the content of the research data	Babian, Carsten - Institute for Legal Medicine, Leipzig University (ORCID: 0000-0002-6621-9705)
Person(s) who is (are) responsible for the content of the research data	Cooney, Gary Sean - Innovation Center Computer Assisted Surgery (ICCAS)
Person(s) who is (are) responsible for the content of the research data	Chalopin, Claire - Innovation Center Computer Assisted Surgery (ICCAS)
Person(s) who is (are) responsible for the content of the research data	Köhler, Hannes - Innovation Center Computer Assisted Surgery (ICCAS) (ORCID: 0000-0001-9342-3288)
Description of further data processing	A support vector machine (SVM) binary classifier was trained for the discrimination of bloodstains of human (n = 20) and five animal species: pig (n = 20), mouse (n = 16), rat (n = 5), rabbit (n = 5), and cow (n = 20). On an independent test set, the SVM model achieved accuracy, precision, sensitivity, and specificity values of 96, 97, 95, and 96%, respectively. Segmented images of bloodstains aged over a period of two months were produced, allowing for the clear visualisation of the discrimination of human and animal bloodstains.
Type of data acquisition	Observation: Spectral imaging
Used research instruments or devices	Specim IQ ® (Specim, Spectral Imaging Ltd., Oulu, Finland)
Research objects	Substance: human and animal blood
Abstract	To address the question of blood origin, the novel application of visible-near infrared hyperspectral imaging (HSI) is used for the detection and discrimination of human and animal bloodstains. The HSI system used is a portable, non-contact, non-destructive method for the determination of blood origin. A support vector machine (SVM) binary classifier was trained for the discrimination of bloodstains of human (n = 20) and five animal species: pig (n = 20), mouse (n = 16), rat (n = 5), rabbit (n = 5), and cow (n = 20).
Applied methods and techniques	Hyperspectral imaging and chemometric methods
Additional descriptive information to understand the data	Data and methods are described in detail in the attached documents and in https://doi.org/10.1007/s12024-023-00689-0.
Counties, the data is referencing	GERMANY	de
Additional keywords	Animal blood · Hyperspectral imaging (HSI) · Support vector machine (SVM) · Neighbourhood component feature selection (NCFS) · Forensics
Language	eng
Year or period of data production	2020-2021
Publication year	2024
Publisher	Universität Leipzig
References on related materials	IsPartOf: 123456789/6055 (Handle)
Content of the research data	Text, Image, Dataset, Software: Text, Image, Dataset: Master Thesis, Journal publication, Measurements
Holder of usage rights	Universität Leipzig
Usage rights of the data	CC-BY-4.0
Additional precise description of discipline	Forensic Science
Discipline(s)	Chemistry	de
Discipline(s)	Engineering	de
Discipline(s)	Medicine	de
Title of the dataset	Discrimination of human and animal bloodstains using hyperspectral imaging