1. Analyzing the effectiveness of the GoogleNet and Resnet models in identifying stress in IT workers.
- Author
-
Raj, M. Prudvi and Kinol, A. Mary Joy
- Abstract
The purpose of this analysis is to determine how well the Resnet and GoogLeNet models detect IT worker stress. Materials and Methods : Using Resnet and Innovative Googlenet, two machine learning algorithms, we can estimate the stress levels of IT workers. Group 1 has 15 samples from Googlenet, while Group 2 contains 15 samples from Resnet. We have thirty participants in our sample. A clinic calc tool was used to conduct the pretest power analysis. The following parameters were used: alpha=0.05, G-power=0.80, last beta=0.2, and CI=95%. Results: The unique Googlenet and Resnet approaches were used to estimate IT staff stress levels, with a 93.62% and 91.15% accuracy rate, respectively. Independent samples t-tests reveal a statistically significant disparity in accuracy between the two algorithms, with a value of 0.001 (p<0.05). Conclusion:For precise stress level prediction among IT staff, the groundbreaking Googlenet architecture has been a watershed moment in AI. Its increased accuracy and reliability in mental health evaluations are a direct result of its outperformance of the Resnet model. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF