Posted November 1, 2007
Archaeological experts from the United States and Canada recently were on the Idaho State University campus to learn how artificial intelligence could aid in artifact identification.
Experts in the nationally recognized ISU National Information Assurance Training and Education Center (NIATEC) enabled researchers from different academic disciplines to design and implement applications for an artificial intelligence classification system. The system is called SIGGI, a nickname for Sigmoid Archaeological Automated Classification System. It mimics the ways humans think, comprehending large numbers of variables that in human minds would require time-consuming analysis.
With SIGGI programmed and operational, archaeologists working in the field could photograph unearthed objects like arrowheads or spear tips, send the pictures to SIGGI and receive an accurate classification report in only a few seconds.
Prominent archaeologists studying artifacts from the Great Plains came to the workshop Sept. 21-23 to provide training for SIGGI and to produce a provisional classification for Northwestern Plains artifacts. They deemed the program a “virtual student,” as they spent hours “teaching” or electronically imparting their own expertise to the system.
The participants spent the days disseminating their knowledge to the system as well as learning how to use it. Researchers will continue to train SIGGI individually through a Web interface, with which they can add new data gathered from their own research expertise and new findings in the coming months.
The automated classification system is already being duplicated by federal and state agencies and researchers for various classification and study purposes.
Principle investigators for the project include Skip Lohse, Ph.D., chair of the ISU anthropology department, and Kandi Turley-Ames, Ph.D., chair of the ISU psychology department. A strong interdisciplinary team consisting of the Informatics Research Institute, psychology and anthropology department personnel and graduate students has also contributed to the development of the technology.
For more information about the research, contact Lohse at (208) 282-5189. For more information about SIGGI, visit http://sands.niatec.iri.isu.edu/NAIDB_Arrow/Default.aspx.