Treffer: Stress prediction in IT employees by image processing using novel KNN algorithm in comparison of accuracy with logistic regression.

The purpose of this study is to examine the relationship between IT employers' mental illness rates and factors including work schedule, personal obligations, and the type of their work. The research is conducted using two distinct ML classifiers: K-nearest neighboring (KNN) and logistic regression (LR). Materials and Methods: During this stage, you'll choose a data collection, train it with the recommended classifiers, and then test it.A dataset of 112 MB of images illustrating human facial expressions was retrieved from the Kaggle website. We train the suggested ML classifier model on an 80% dataset and test it on a 20% dataset. For SPSS analysis, the output of two classifiers is divided into two groups, with a total of twenty output values from different functional operations. Each group contains ten values. After doing the SPSS analysis, the CI metric came out at 0.292 and the alpha metric to 0.95.Results: An experimental study was conducted using the Python compiler to examine the accuracy improvement of two classifiers in identifying IT employee stress-related theft. Compared to the LR classifier's 87.12% accuracy, the chosen KNN classifier achieved a far higher rate of 95.67%. Based on these results, it seems that the KNN classifier made more accurate identifications of IT staff theft caused by stress. Two categories were determined to have a significant statistical impact, with a p-value of 0.002 (p<0.05). Conclusion: Psychological stress is detrimental to physical health. It is essential to recognize and control stress before it becomes severe. Simple solutions are affordable and easy to get. This device may detect if the user is nervous or relaxed by secretly analyzing their social media interactions and other data. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)