Indonesia Conference Directory

The need for aroma recognition devices or often known as enose (electronic nose) is increasing. In the field of health, enose is able to detect early type 2 diabetes mellitus (DM) from urine aroma. Enose is an aroma recognition tool that uses a pattern recognition algorithm to recognize urine aromas from diabetes mellitus patients based on input signals from gas sensor arrays. The need for portable enose devices is increasing, because of the increasing need for real-time needs. This has a large impact on the selection of the number of gas sensor arrays in the enose. This article discusses the effect of the number of sensor arrays used on the results of the introduction. Enose uses a maximum of 4 sensors, with a maximum feature matrix. After that, the characteristic matrix enters the feature extraction of PCA (Principle Component Analysis) and clustering using the FCM (Fuzzy C Means) method. Variations in the number of sensors consist of 1 sensor, 2 sensors, 3 sensors and 4 sensors. The sensor used consists of MQ2, MQ5, MQ6 and MQ8. The results of the introduction show that, enose using 2 sensors has a high accuracy of 98.3%.