AI-assisted Chemical Sensing (HyperTaste)

The effective investigation of our chemical environment is key to countless innovations and applications in materials science, sustainability, food science, and health. Multi-sensor systems such as electronic tongues and electronic noses have been explored in the last decades as a means to conduct complex analysis of chemical systems in shorter time than conventional approaches based on established analytical instrumentation or human sensory experts.

With HyperTaste, we introduce an AI-assisted and data-driven framework for supervised and unsupervised analysis of complex liquids. Our approach relies on the combination of an AI pipeline with remarkably simple multi-sensor hardware for use in various computing environments including deployment as a mobile app. As the functionality of HyperTaste is defined by software, the same system can be easily reconfigured for different tasks simply by training with examples. The implications are profound, with our research collaborations demonstrating the capability to validate the chemical composition and properties of products in minutes instead of hours, at a fraction of the cost, and even outside of conventional laboratory environments.

Awards

• Best Live Demo, IEEE Sensors, Dallas, TX, USA, 2022
• Best Young Professional Poster, IEEE Sensors, Dallas TX, USA, 2022
• Best Industrial Presentation, International Symposium on Olfaction and Electronic Nose (ISOEN), Aveiro, Portugal, 2022