Machine Learning Techniques for Classification of Stress Levels in Traffic

Fenerich, Amanda Trojan ^[3] ; Romanelli, Egídio José ^[1] ; Catai, Rodrigo Eduardo ^[4] ; Steiner, Maria Teresinha Arns ^[2]
1. [1] Universidade Federal do Paraná
  
  Universidade Federal do Paraná
  
  Brasil
2. [2] Pontifícia Universidade Católica do Paraná
  
  Pontifícia Universidade Católica do Paraná
  
  Brasil
3. [3] University of Galway
4. [4] Federal University of Technology Paraná
Mostrar afiliaciones +
Localización: Socioeconomic Analytics, ISSN-e 2965-4661, Vol. 2, Nº. 1, 2024, págs. 84-93
Idioma: inglés
Enlaces
- Texto completo
Resumen
- The aim of this study is to apply Machine Learning techniques for predicting and classifying the stress level of people commuting from home to work and also to evaluate the performance of prediction models using feature selection. The database was obtained through a structured questionnaire with 44 questions, applied to 196 people in the city of Curitiba, PR. The classification algorithms used were Support Vector Machine (SVM), Bayesian Networks (BN), and Logistic Regression (LR), comparatively. The results indicate that the classification of stress levels of new instances (people) as “high” or “low” can be performed using the LR technique (presenting the highest accuracy, 83.67%).