12.7 Forensic Data Mining

Neural network have been used to recognize signatures in seized drugs and arson cases; for example, Casale and Watterson produced a paper on "A Computerized Neural Network Method for Pattern Recognition of Cocaine Signatures," which describes a practical procedure for rapidly searching a large database of cocaine signatures to identify database entries that closely resemble a given reference cocaine exhibit. Their procedure takes advantage of the pattern-recognition capability of the multilayer perceptron neural network to identify similar cocaine signatures.

Their pattern-recognition software has been used on a daily basis at the North Carolina State Bureau of Investigation (NCSBI) to aid forensic experts in identifying signatures that originate from the same batch of cocaine. Intelligence reports generated from database searches have been useful to undercover field agents who are striving to build drug-related conspiracy cases. The software was developed as a collaborative effort between the NCSBI and the Center for Systems and Engineering of the Research Triangle Institute.

Another forensic investigator, S.A. Barshick, conducted an analysis of accelerants and fire debris using aroma-detection technology similar to the work done by Matt Vona from the California Department of Justice. Barshick investigated the utility of electronic aroma-detection technologies for the detection and identification of ignitable liquid accelerants and their residues in suspected arson debris.

Through the analysis of known accelerants and residues, a trained neural network was developed for classifying fire-debris samples. Three unknown items taken from actual fire debris that had contained gasoline, kerosene, and diesel fuel were classified using the neural network. One item, taken from the area known to have contained diesel fuel, was correctly identified as diesel fuel residue every time. Barshick also reported success in using neural networks in the classification of kerosene and gasoline residues. His paper, "Analysis of Accelerants and Fire Debris Using Aroma Detection Technology" can be found on the Journal of Forensic Science Web site.