Machine Learning Models for Predicting Anthropometric Measurements in School Aged Children for Ergonomic Classroom Furniture

EasyChair Preprint 14325

Abstract

The design of ergonomic classroom furniture tailored to the specific anthropometric measurements of school-aged children is crucial for promoting comfort, posture, and overall well-being. This study explores the application of machine learning models to predict anthropometric measurements, aiming to optimize the design process of classroom furniture. Anthropometric data, including height, weight, sitting height, and limb lengths, were collected from a diverse sample of children aged 6 to 12 years. Various machine learning algorithms, such as linear regression, decision trees, random forests, and neural networks, were employed to develop predictive models.

The performance of these models was evaluated using metrics like mean squared error (MSE), mean absolute error (MAE), and R-squared (R²) values. The results demonstrated that ensemble methods, particularly random forests, provided the highest accuracy in predicting anthropometric measurements. Additionally, feature importance analysis highlighted key predictors such as age, gender, and weight, offering valuable insights into the most influential factors affecting anthropometric outcomes.

The study underscores the potential of machine learning in enhancing the ergonomic design of classroom furniture, leading to improved health and academic performance among school-aged children. Future research directions include the integration of real-time data collection using wearable devices and the development of adaptive furniture systems that adjust to individual anthropometric changes over time.

Keyphrases: 1. Ergonomic classroom furniture, 10. Real-time data collection, 11. Adaptive learning models, 12. Customizable furniture design, 13. Student comfort, 14. Posture support, 15. Musculoskeletal health, 16. Cross-validation, 17. Hyperparameter tuning, 18. Predictive accuracy, 19. Educational ergonomics, 2. Anthropometric measurements, 20. Interdisciplinary research, 3. Machine learning models, 4. School-aged children, 5. Predictive modeling, 6. Data privacy, 7. Ethical considerations, 8. Model generalization, 9. Ensemble methods

@booklet{EasyChair:14325,
  author    = {Wayzman Kolawole},
  title     = {Machine Learning Models for Predicting Anthropometric Measurements in School Aged Children for Ergonomic Classroom Furniture},
  howpublished = {EasyChair Preprint 14325},
  year      = {EasyChair, 2024}}