K-Nearest Neighbor Classification Based on Gas Array Sensor to Detect Borax in Meatballs

Borax is a white powder consisting of colorless crystals and easily soluble in water. This chemical can also be used to separate gold from ore to replace the use of mercury. It is very dangerous if chemicals such as borax are used illegally and mixed into processed foods such as meatballs and eaten by humans continuously over a long period of time. The use of borax as a preservative in food is difficult to recognize with the naked eye. The test that is usually carried out to see the borax content in food is a laboratory test. So it is necessary to apply technology to overcome this problem. In recent years, a lot of research has been carried out to identify borax levels in food, one of which is by using a series of gas sensors as an electronic smell (e-nose). The focus of this research is to detect processed meatball foods that contain borax by classifying them using the KNN method and using the Enose sensor series based on gas sensors from the Figaro manufacturer, namely the TGS gas sensor series. The TGS gas sensor response combined with the K-Nearest Neighbor (KNN) method shows that the sensor can classification the gas in meatballs with and without borax into two types. Determining the number of neighbors (K) that will be used to consider class determination. The research results obtained an accuracy value of 100% for K=1, K=3, K=5 and K=9 and 90% for K=11.