State-of-the-Art of Prediction of Stress Levels in the Workplace Based on MLP-CNN Technique

When both mental and bodily functions deviate from their usual patterns of action, symptoms of stress become apparent. Management style and a lack of autonomy over one's work are two of the many potential sources of stress in the workplace. Both employers and employees benefit from manageable levels of stress. Both individual and organisational objectives can be advanced using this method. Workers' physical, mental, and emotional health may all take a hit when they're under too much stress. Psychological techniques that make use of questionnaires provide one approach to stress evaluation. Model training, feature extraction, feature selection, and preprocessing all rely on sequencing. The term “data preprocessing” describes the steps taken to prepare raw data for usage in machine learning or deep learning models. The process of feature extraction is crucial in order to construct new features from pre-existing ones in the dataset. Feature selection is the process of selecting features that will be most helpful in predicting the results of the classification. Careful handling of features is required during training of an MLP-CNN model. The proposed method completely outperforms the state-of-the-art algorithms, MLP and CNN. An astounding 98.43% accuracy grade was shown in the results, indicating significant improvement.