Washington University Department of Electrical Engineering     

Characterizing Odors Using Electronic

Nose Sensors

Introduction

Abstract:
The goal of this project is to understand the responses of electronic nose sensors when exposed to specific food odors. In order to achieve this, we built an experimental setup consisting of an array of three chemical sensors, their corresponding signal conditioning circuitry, and a data acquisition device.  For acquiring and processing the data measurements, we implemented a graphical user interface (GUI) in Labview. We developed a protocol for calibrating the sensor responses to odorless air such that useful signals are obtained when the sensor array is exposed to food odors.  We built characterization profiles on the nuts based on the sensor measurements.

 

Algorithms were then developed to sort through the data and identify what type of nut each data point represented. It was discovered that the k-nearest neighbor algorithm performed nut classification better than the k-means algorithm.

 

Background:

Electronic sensing technology is a developing field of study that has greatly advanced over the last decade in technical and consumer applications. Electronic noses are already being introduced in research laboratories, manufacturing processing technology, home and workplace safety monitoring and quality control. Currently, most of the research done has been on classifying odors within a specific category of sample odors.  Eventually electronic nose technology is expected to be able to detect and distinguish specific odors and the particular compounds within the odor. This monumental advancement can be applied for use in specific compound detection systems, such as medical diagnostic tools.

We chose to use almonds, peanuts and hazelnuts because of their accessibility and ease-of-storage.

The designed GUI and experimental setup can be used as a starting point for future research exploring chemical array signal processing applications, such as food classification and chemical source localization.

 

The preliminary poster used at the Fall 2009 Undergraduate Research Symposium can be found here.