Evaluation method of Driver’s olfactory preferences: a machine learning model based on multimodal physiological signals
2024

Evaluating Drivers' Smell Preferences with Machine Learning

Sample size: 33 publication Evidence: moderate

Author Information

Author(s): Tang Bangbei, Zhu Mingxin, Hu Zhian, Ding Yongfeng, Chen Shengnan, Li Yan

Primary Institution: School of Intelligent Manufacturing Engineering, Chongqing University of Arts and Sciences, Chongqing, China

Hypothesis

Can physiological signals be used to assess drivers' olfactory preferences effectively?

Conclusion

The study shows that a machine learning model can accurately classify drivers' olfactory preferences using physiological signals.

Supporting Evidence

  • The decision tree model achieved the highest classification accuracy of 88%.
  • Physiological signals were collected in real driving environments to enhance data accuracy.
  • Baseline processing improved model accuracy by 3.50% and F1-score by 6.33%.

Takeaway

This study helps understand what smells drivers like while driving, which can make their experience more comfortable.

Methodology

A machine learning model was developed using physiological signals from 33 drivers to classify their olfactory preferences.

Potential Biases

Potential biases due to the limited diversity of the sample and the subjective nature of olfactory preferences.

Limitations

The study's sample size and age range may limit the generalizability of the findings.

Participant Demographics

33 drivers (16 males and 17 females) aged 21 to 32 years with an average driving experience of 3.7 years.

Digital Object Identifier (DOI)

10.3389/fbioe.2024.1433861

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication