Designing an E-Nose Prototype Based on Gas Sensors Array

Nowadays, electronic olfaction or Electronic Noses (E-Noses) are mostly designed and developed for lab-based applications. In real-life scenarios, smell detection represents the external and internal responses to human being events. In Human Computer Interaction (HCI), detecting odorant molecules in the air plays a very important role in different conditions such as food quality, environmental monitoring, and security. Few real-time applications based on E-Nose have been developed, such as biosensors based on insect antenna or small drones with low-cost gas sensors. Smell detection and recognition as an environmental monitoring application using sensor array measurements represent the scope of this work. To increase the accuracy and application range of detection, six of high and low-quality sensors have been used to get measurements. In this study, the proposed E-Nose prototype consists of DF-NH3, MQ-136, MQ-135, MQ-8, MQ-4, and MQ-2 sensors. This work presents the methodology in terms of artificial intelligence techniques used for classification and object detection such as machine learning classification, clustering and regression algorithms. Using the K-Nearest Neighbors (KNN) algorithm, these sensors used in the experimental results were able to predict petrol, gasoline, perfumes, and others with a 71.1% accuracy rate.