(Nanowerk News) Imagine if you could ask a machine to “smell” something for you with just the click of a button. That’s what electronic noses, or e-noses, are for. They are systems that combine chemical gas sensors, signal processing and machine learning algorithms to mimic the sense of smell. E-noses can be used for a variety of purposes, such as checking food quality, monitoring air pollution, diagnosing disease and detecting explosives.
How do they work? What are the challenges and opportunities in this field? A team led by Jingdong Chen of Northwestern Polytechnical University in Xi’an, China and Weiwei Wu of Xidian University in Xi’an, China recently explored these questions in a comprehensive review of methods and algorithms developed for e-commerce. noses. The review discusses the limitations of current gas sensors and provides an overview of the algorithm design.
The review was published in Intelligent Computing (“Algorithmic Design Review on Electronic Nose: Challenges, Status, and Trends”).
E-noses artificially mimic a biological sense of smell. The gas sensors of e-noses correspond to biological olfactory receptor neurons. When you sniff something, small molecules float in the air and enter your nose. Similarly, gas sensors can capture molecules in the air through the air intake system. The sensor reacts to these molecules and changes in ways that can be measured by electronic signals. These signals are then converted from an analog format to a digital format so that the computer can use algorithms to analyze and interpret the data.
The review summarizes the existing methods and algorithms in the field of e-noses, grouping them according to a classification framework that highlights the challenges presented by the following limitations of gas sensors:
Despite the significant progress made in recent decades, the large-scale adoption of e-noses in practical applications still has a long way to go.
The authors of the review believe that ensuring the robustness of the e-nose system should be a top priority for future research and development. While odor identification and intensity quantification have been extensively investigated, there are several important tasks that demand greater attention. This includes interference suppression and recognition, optimization of sensor arrays, detection of sensor deviations and failures, noise reduction and utilization, and defining detection limits, among others. In addition, they say it is important to learn the basic mathematical model of the sensing mechanism, which is the basis for solving many problems related to e-noses.