The detection and classification of food flavours are critical in the food industry for quality control, product development, and food authentication. Traditional analytical methods such as gas chromatography-mass spectrometry (GC-MS) provide high precision but are often expensive, time-consuming, and require specialised training. Recent advancements in miniaturised electronic nose (e-nose) technology offer a potential alternative for rapid, cost-effective, and portable flavour detection. Inspired by recent developments in high-speed e-nose systems, this project aims to develop an application-specific e-nose for food flavour analysis, optimised for rapid detection using advanced machine learning algorithms.
Project Aim
This project seeks to develop and optimise an electronic nose (e-nose) system for detecting and classifying food flavours. Unlike conventional e-nose platforms, this system will utilise an existing miniaturised hardware setup (please see this paper for reference) but focus on improving signal processing and machine learning algorithms to enhance detection speed and accuracy. The e-nose will be trained using a selection of characteristic flavour compounds commonly found in food.
School
Chemical Engineering
Research Area
Food chemistry | Sensory evaluation | Rapid testing using electronic device
- Research environment
- Expected outcomes
- Supervisory team
- Reference material/links
- This project offers a unique opportunity to develop a miniaturised electronic nose (e-nose) for rapid food flavour detection. Students will gain hands-on experience in sensor integration, machine learning, and data analysis in a multidisciplinary research environment. Collaboration with experts in food chemistry and AI-driven sensing will enhance technical skills, and publishing the results is also possible.
- A working prototype of a food flavour e-nose with optimised algorithms for rapid detection.
- A dataset of e-nose sensor responses correlated with GC-MS data for validation.
- Insights into the applicability of machine learning for flavour detection in food quality control.
Significance
This project will contribute to the development of fast, low-cost flavour detection technologies, providing valuable applications in food safety, quality control, and sensory analysis. By refining the data processing and machine learning components, this study aims to push the boundaries of electronic olfaction for food applications.
- Barea-Ramos, J. D., Cascos, G., Mesías, M., Lozano, J., & Martín-Vertedor, D. (2022). Evaluation of the olfactory quality of roasted coffee beans using a digital nose. Sensors, 22(22), 8654. https://doi.org/10.3390/s22228654
- Liu, L., Na, N., Yu, J., Zhao, W., Wang, Z., Zhu, Y., & Hu, C. (2023). Sniffing like a wine taster: Multiple overlapping sniffs (MOSS) strategy enhances electronic nose odor recognition capability. Advanced Science, 11, 2305639. https://doi.org/10.1002/advs.202305639
- Gonzalez Viejo, C., Fuentes, S., Godbole, A., Widdicombe, B., & Unnithan, R. R. (2020). Development of a low-cost e-nose to assess aroma profiles: An artificial intelligence application to assess beer quality. Sensors and Actuators B: Chemical, 308, 127688. https://doi.org/10.1016/j.snb.2020.127688
- Gonzalez Viejo, C., Tongson, E., & Fuentes, S. (2021). Integrating a low-cost electronic nose and machine learning modelling to assess coffee aroma profile and intensity. Sensors, 21(6), 2016. https://doi.org/10.3390/s21062016
- Dennler, N., Drix, D., Warner, T. P. A., Rastogi, S., Della Casa, C., Ackels, T., Schaefer, A. T., van Schaik, A., & Schmuker, M. (2024). High-speed odor sensing using miniaturized electronic nose. Science Advances, 10(eadp1764). https://doi.org/10.1126/sciadv.adp1764