Interdisciplinary problem-solving skills are a key educational objective in modern STEM fields. However, our current education system is faced with the challenge of instructing materials chemistry, electronics, and data analysis in isolation. This work reports a modular instructional framework on machine learning-assisted electronic nose to support undergraduate chemical education. Using low-cost volatile organic compound sensors and accessible data acquisition and analysis tools, this framework aims to guide students through the complete sensing workflow, including sensor operation, hardware design and configuration, data acquisition, feature extraction, and machine learning based classification. The integration of components from different disciplines helps students connect conceptual knowledge with practical implementation. The modular structure of this framework allows readily adaptation to various educational settings. It also incorporates opportunities for science communication, such that students can translate technical concepts for nonexpert audiences and relate the obtained knowledge skills to real-world applications. Demonstrations using the resulting electronic nose (e-nose) to analyze various food odors were conducted to examine the viability of this instructional framework. The affordability and user-friendly design of this education framework enable educators at different institutions to incorporate the provided resources into their teaching practices in various formats.
Yang et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: