Detecting Pork Adulteration in Beef for Halal Authentication Using an Optimized Electronic Nose System

Recently, the issue of food authentication has gained attention, especially halal authentication,
because of cases of pork adulteration in beef. Many studies have developed rapid detection for adulterated
meat. However, these studies are not yet practical and economical methods and instruments and a faster
analysis process. In this context, this paper proposes the Optimized Electronic Nose System (OENS) for
more accurately detecting pork adulteration in beef. OENS has advantages such as proper noise �ltering,
an optimized sensor array, and optimized support vector machine (SVM) parameters. Noise �ltering
is carried out by cross-validation with different mother wavelets, i.e., Haar, dmey, coi�et, symlet, and
Daubechies. The sensor array was optimized by dimension reduction using principal component analysis
(PCA). An algorithm is proposed for the optimization of the SVM parameters. An experiment was conducted
by analyzing seven classes of meat, comprising seven different mixtures of beef and pork. The �rst and
seventh classes were 100% beef and 100% pork, respectively, while the second, third, fourth, �fth, and sixth
classes contained 10%, 25%, 50%, 75%, and 90% of beef in a sample of 100 grams, respectively. Sample
testing was carried out for 15 minutes for each sample. The classi�cation test results to detect beef and
pork had an accuracy of 98.10% using the optimized support vector machine. Thus, OENS has a favorable
performance to detect pork adulteration in beef for halal authentication.