Optimizing the Failure Prediction in Deep Learning

Main Article Content

Himangi, Prof. (Dr.) Mukesh Singla

Abstract

 


Avatars are computer-generated digital representations that people may use in the Predicting issues with software systems built from modules is the focus of this research. This data collection was used as a reference in order to accomplish this objective. The evaluation framework for reusable software components is provided by this research. The dataset of factors that play a role in the decision-making process has been run through the PSO algorithm. The primary objective is to provide a clever and time-saving method of choosing components. After filtering for ideal values, the dataset is utilized to train a deep learning model. Accuracy measurements including recall value, precision, and F1 score will be used to evaluate the effectiveness of the optimized component selection model. This research is significant because it provides a high-performance and accurate solution to a major problem in predicting. We have done our best to estimate the number of lines of code, the complexity, the design complexity, the projected time, the difficulty, the intelligence, and the efforts required. A model for discovering mistakes has been developed after the dataset was filtered to account for the ideal value. By keeping just the most crucial characteristics and getting rid of all optimized data, we have made the model more trustworthy.


 

Downloads

Download data is not yet available.

Article Details

How to Cite
Himangi, Prof. (Dr.) Mukesh Singla. (2023). Optimizing the Failure Prediction in Deep Learning. International Journal of New Practices in Management and Engineering, 11(01), 61–67. Retrieved from https://www.ijnpme.org/index.php/IJNPME/article/view/195 (Original work published March 16, 2022)
Section
Articles
Author Biography

Himangi, Prof. (Dr.) Mukesh Singla