Project Details
Description
Improvised Explosive Devices (IEDs) and the terrorist networks that employ them pose a current and future threat throughout the world. An ongoing challenge is identifying the linkages and relationships between the individuals that form these terrorist network. However, this information is essential if these networks are to be disrupted.
This research utilises the novel application of data science and machine learning techniques to analyse chemical test data from recovered samples of explosives, with the aim of identifying matches and relationships between the samples. Previously, forensic chemists have demonstrated the ability to identify matches between explosive samples through chemical analysis. However, this analysis was a manual and time-consuming process using advanced chemical testing techniques and could not be applied at a large scale. The use of data science aims to reduce the need for advanced testing and enable rapid analysis of large data sets.
The research methodology combines machine learning clustering techniques with traditional chemometric techniques for analysing chemical test data. Data pre-processing techniques have been researched to improve clustering outcomes and assessment metrics have been developed to assess the goodness of clustering. Data fusion techniques are also utilised to analyse data from multiple disparate tests applied to each explosives sample. The intended result of this analysis is confident matching of explosive samples; inferring they are made by the same bombmaker, or, matching of common characteristics within differing explosive samples; inferring linkages between different bombmakers.
This research utilises the novel application of data science and machine learning techniques to analyse chemical test data from recovered samples of explosives, with the aim of identifying matches and relationships between the samples. Previously, forensic chemists have demonstrated the ability to identify matches between explosive samples through chemical analysis. However, this analysis was a manual and time-consuming process using advanced chemical testing techniques and could not be applied at a large scale. The use of data science aims to reduce the need for advanced testing and enable rapid analysis of large data sets.
The research methodology combines machine learning clustering techniques with traditional chemometric techniques for analysing chemical test data. Data pre-processing techniques have been researched to improve clustering outcomes and assessment metrics have been developed to assess the goodness of clustering. Data fusion techniques are also utilised to analyse data from multiple disparate tests applied to each explosives sample. The intended result of this analysis is confident matching of explosive samples; inferring they are made by the same bombmaker, or, matching of common characteristics within differing explosive samples; inferring linkages between different bombmakers.
Status | Active |
---|---|
Effective start/end date | 24/07/18 → … |
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.
Datasets
-
FTIR spectroscopy of representative homemade explosive detonators
Crase, S. (Creator) & Hall, B. (Creator), Charles Darwin University, 10 May 2021
DOI: 10.25913/7bh8-bv76
Dataset
File