Search

The use of PPE is closely related to occupational diseases caused by work factors or diseases acquired while doing work and occur over a long period. This study aimed to determine the relationship between Knowledge, Compliance with the use of PPE, Availability of PPE, Implementation of Standard Operating Procedures (SOP) for the use of PPE and PPE Implementation Policy with Occupational Disease Risk Control. This research is quantitative with an analytic survey approach using a cross-sectional study method. The population in this study were all health workers with a total sample of 28; the sample was all nurses/doctors and midwives. Based on the square or comparative test results to determine the relationship between occupational disease risk control. The results showed that there was no relationship between knowledge (P=0.608), there was a relationship between the availability of Personal Protective Equipment (PPE) (P=0.002), Standard Operating Procedures (SOP) (P=0.004), Compliance with using Personal Protective Equipment (PPE) (P = 0.000). There is no relationship between policy (P = 0.0604) and controlling the risk of occupational diseases. Interventions are needed to ensure the availability of personal protective equipment (PPE) such as masks, and protective goggles, adherence to the use of self- protection equipment (PPE), and the implementation of Standard Operating Procedures (SOP) in each unit requires complete control so that the Standard Operating Procedures (SOP) are implemented, and adherence to the use of Personal Protective Equipment (PPE) requires awareness/not negligence in using Personal Protective Equipment (PPE) when serving patients to avoid risks occupational illness.

This research is based on a significant problem in credit risk analysis in the banking sector caused by class imbalance. We face the problem of the model’s inability to accurately identify risks in the ‘‘Charged Off’’ class. As a solution, we propose a stacked ensemble approach that utilizes synthetic minority over-sampling technique (SMOTE) to balance the class distribution. Experiments were conducted by applying SMOTE to the training data before training the credit model using gradient boosting (XGBoost) and random forest (RF) algorithms in a single ensemble. The results show significant improvements in precision, recall, and F1-score after applying SMOTE on the unbalanced classes. The updated model achieved a striking accuracy rate of 0,97 on resampled training data. This re-search clearly identifies the problem of class imbalance as a major challenge in credit risk analysis. The application of SMOTE in a stacked ensemble was found to be effective in improving model performance, making a valuable contribution to the development of more reliable credit models for better risk management and revenue generation in financial institutions. [ABSTRACT FROM AUTHOR]