OdorIQ: Smell Identification Using AI and Machine Learning

Overview

We can use electronics to see, hear, and communicate, but we still need a way to use electronics to smell things and send smells over distances. By creating a way to do this, we can identify dangerous gases, check food quality, and implement environmental measures. It also has purposes in medicine to identify different diseases or to help those who can't smell well, like those affected by COVID-19. It may also have entertainment purposes like smelling food on TV. That led me to create a project, OdorIQ, a system that can electronically identify food from its smell through gas sensors and AI/ML. The goal is to create a digital nose similar to our sense of smell. OdorIQ integrates multiple gas sensors that detect a range of food odors as a composition of Volatile Organic Compounds (VOCs.) These sensors capture data processed through a machine-learning framework and create a model that is trained to recognize and classify various food scents based on their unique patterns. The experiment involved using gas sensor technology to collect food odor data as a composition of VOCs while meticulously training and testing AI/ML models to identify smells of various foods (garlic, coffee, etc.) Currently, the prototype identifies various smells but, in the future, I plan to evolve the platform with more sensitive sensors and more powerful cloud computers to identify smells faster and more accurately, attempting to make my prototype more capable of practical applications in the real world.

Competition history

• AJAS 2025 Category not listed

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

• AJAS None projects
• Every AJAS 2025 project