DOI 10.1016/j.microc.2021.106893 KEYWORDS gasoline; research octane number; HS-MS eNose; NIRS; chemometrics; support vector machine; random forest; low-level data fusion ABSTRACT In the quality control of flammable and combustible liquids, such as gasoline, both rapid analysis and automated data processing are of great importance from an economical viewpoint for the petroleum industry. The present work aims to evaluate the chemometric […]