Syracuse University Team Uses Input From the Field to Develop New Technology
Criminal justice practitioners, faced with what seems like an overwhelming amount of information on technology research and innovation, may often wish for additional materials that answer the question: What’s in it for me?
With its review of technology developed under National Institute of Justice (NIJ) grants and follow-up success stories, the NIJ Forensic Technology Center of Excellence (NIJ FTCoE) attempts to produce quick-read publications that do exactly that.
One such recent publication, NIJ and Syracuse University: Improving DNA Mixture Interpretation with the Help of Machine Learning, focuses on the Probabilistic Assessment for Contributor Estimation (PACETM) tool, which uses machine learning as a method of DNA mixture interpretation that runs on standard computers and provides an estimate of individual contributors to a DNA sample at a 98-percent accuracy rate in a few seconds.
As the success story explains, DNA samples often are a mix of material from multiple individuals. The first step in interpreting such a mixture is determining how many individuals contributed to the sample; the more individuals, the harder it is to make that determination, which previously relied on human interpretation. The research team, Dr. Michael Marciano and Jonathan Adelman of Syracuse University’s Forensic and National Security Sciences Institute, collected feedback from several agencies and practitioners to help inform the design and development of the software, and are currently training end users of the tool in workshops.
“The development of a commercially available software from NIJ-funded research is truly a success story,” says FTCoE Innovation Analyst Rebecca Shute, “and there are three important factors that contributed to the successful transition of this technology. First, the team engaged with the Syracuse University Technology Transfer Office, which supported the team through the process of licensing their technology. Second, Dr. Marciano was a casework analyst before he became a researcher, and that helped bring the end-user perspective into software development. And finally, the team engaged a lot of development partners, whose input ultimately added value to the project.”
That approach will continue as the Syracuse team uses additional NIJ funding to apply PACE to next generation DNA sequencing, the cutting edge of sequencing techniques that provides higher and faster throughputs. (The current version of PACE works with STR-based sequencing, the method currently used in most laboratories). Other efforts involve investigating the use of machine learning to enhance current methods of latent print analysis and drug identification.
The current version of PACE is currently licensed through NicheVision Forensics, LLC, as is training in its use.
“The key takeaway for criminal justice agencies about this and other similar research projects is that their participation is crucial to getting technologies from research to practice in the field. Even though practitioners aren’t the ones inventing the technologies, they play a vital role in validation and testing,” Shute says.
Download NIJ and Syracuse University: Improving DNA Mixture Interpretation with the Help of Machine Learning from the NIJ FTCoE here.
Article photo: vitstudio/Shutterstock.com