3.8 Proceedings Paper

Men and Women Classification at Night Through the Armpit Sweat Odor using Electronic Nose

Publisher

IEEE
DOI: 10.1109/APWIMOB51111.2021.9435273

Keywords

ANNOVA; Electronic Nose; Gender; Machine Learning

Funding

  1. Special Program for Research Against COVID-19 (SPRAC)
  2. Indonesian Ministry of Research and Technology or National Agency for Research and Innovation
  3. Indonesian Ministry of Education and Culture under Penelitian Terapan Unggulan Perguruan Tinggi (PTUPT) Program
  4. PMDSU Program

Ask authors/readers for more resources

Nighttime sweating may indicate a disturbance in the human metabolic system, and research has found that distinguishing between men and women based on armpit sweat odor can reveal varying tendencies for disease. By utilizing gas sensors, it was discovered that women are more likely to suffer from certain illnesses, such as leukemia, based on volatile organic compound (VOC) measurements.
Sweating at night can be an indication that there is a disturbance in the human metabolic system. Sweat itself is a substance that is unused in the body or the result of human excretion. The sweat glands are scattered in all parts of the body, but mostly in three locations: armpits, palms, and feet. Several kinds of research related to sweat and Electronic Nose (E-Nose) have also been studied. The study used a patch to absorb sweat and proved the presence of nicotine content from a smoker. However, the previous research has not focused on human sweat at night for potential disease. This paper aims to propose a system to distinguish men and women at night through the armpit sweat odor using Taguchi Gas Sensors (TGS) and SHT15. Researchers found four significant sensors for further investigation: TGS 822, TGS 826, TGS 833, and TGS 2620. This study obtained a total of 165 armpit sweat data, which have been processed and adjusted for this case into 25 data, 12 men (ME) and 13 women (WO). Several classification models are implemented, such as Support Vector Machine (SVM), Naive Bayes (NB), and Decision Tree (DT) with accuracy 92.30%, 96.15%, and 84.62%, respectively. Based on the highest accuracy and the Volatile Organic Compounds (VOC) measurement, women are more likely to suffer from several diseases than men, such as leukemia.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available