Bootlegged alcoholic beverages are a big business with damaging and occasionally lethal consequences. There are many excellent analytical techniques to detect these forgeries, but they require destructive sampling. How does one test a bottle quickly without opening it? NIR spectroscopy has been used to measure ethanol and methanol in situ. The problem is that commercial bottles come in all sorts of shapes and sizes, which distort the light path. This publication describes a machine-learning approach to obtain robust classifications.
Large J., Kemsley E.K., Wellner N., Goodall I., Bagnall A. (2018) Detecting Forged Alcohol Non-invasively Through Vibrational Spectroscopy and Machine Learning. In: Phung D., Tseng V., Webb G., Ho B., Ganji M., Rashidi L. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2018. Lecture Notes in Computer Science, vol.10937, pp 298-309. Springer, Cham.