원문정보
초록
영어
This study explores the use of a Deep Autoencoder model to predict depression among plant and machine operators, utilizing data from the Korean National Health and Nutrition Examination Survey (KNHANES, n=3,852). The Deep Autoencoder model outperformed the Logistic Regression, Naive Bayes, XGBoost, and LightGBM models, achieving an accuracy of 86.5%. Key factors influencing depression included work stress, exposure to hazardous substances, and ergonomic conditions. The findings highlight the potential of the Deep Autoencoder model as a robust tool for early identification and intervention in workplace mental health.
목차
Abstract
1. Introduction
2. Materials and Methods
2.1. Design and Subject
2.2. Data Collection
2.3. Input Variables
2.4. Data Preprocessing
2.5. Machine Learning Models
2.6. Deep Autoencoder Model
2.7. Model Training and Evaluation
2.8. Feature Importance
3. Results
3.1. Descriptive Statistics
3.2. Model Performance
3.3. Model Performance Comparison
3.4. Feature Importance
3.5. Feature Importance Analysis
4. Discussion
5. Discussion
References
1. Introduction
2. Materials and Methods
2.1. Design and Subject
2.2. Data Collection
2.3. Input Variables
2.4. Data Preprocessing
2.5. Machine Learning Models
2.6. Deep Autoencoder Model
2.7. Model Training and Evaluation
2.8. Feature Importance
3. Results
3.1. Descriptive Statistics
3.2. Model Performance
3.3. Model Performance Comparison
3.4. Feature Importance
3.5. Feature Importance Analysis
4. Discussion
5. Discussion
References
키워드
저자정보
참고문헌
자료제공 : 네이버학술정보