Fire accelerant classification from GC-MS data of suspected arson cases using machine-learning models

Using a practical GC-MS dataset containing approximately 4000 suspected arson cases, three machine-learning based classification models were developed and their performances were evaluated. All models trained for classifying the data from fire residue into six categories; no fire accelerants detected or else one of fire accelerants was used within gasoline, kerosene, diesel, solvents, or candle. The classification accuracies of the random forest, supporting vector machine, and convolutional neural network model were 0.88, 0.88, and 0.92, respectively. By calculating feature importance of the random forest model, several potential chemical fingerprints of fire accelerants were discovered.