This paper is published in Volume-8, Issue-4, 2022
Area
Computer Science
Author
Vishal Thakur, Ashok Kumar Kashyap, Aditi Badhan
Org/Univ
University Institute of Information Technology, Himachal Pradesh University, Shimla, Himachal Pradesh, India
Keywords
Data Science, Datamining, Software Defect, Deep Learning, Machine Learning
Citations
IEEE
Vishal Thakur, Ashok Kumar Kashyap, Aditi Badhan. Software Defect Prediction by Data Science and Machine Learning Approaches, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.
APA
Vishal Thakur, Ashok Kumar Kashyap, Aditi Badhan (2022). Software Defect Prediction by Data Science and Machine Learning Approaches. International Journal of Advance Research, Ideas and Innovations in Technology, 8(4) www.IJARIIT.com.
MLA
Vishal Thakur, Ashok Kumar Kashyap, Aditi Badhan. "Software Defect Prediction by Data Science and Machine Learning Approaches." International Journal of Advance Research, Ideas and Innovations in Technology 8.4 (2022). www.IJARIIT.com.
Vishal Thakur, Ashok Kumar Kashyap, Aditi Badhan. Software Defect Prediction by Data Science and Machine Learning Approaches, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.
APA
Vishal Thakur, Ashok Kumar Kashyap, Aditi Badhan (2022). Software Defect Prediction by Data Science and Machine Learning Approaches. International Journal of Advance Research, Ideas and Innovations in Technology, 8(4) www.IJARIIT.com.
MLA
Vishal Thakur, Ashok Kumar Kashyap, Aditi Badhan. "Software Defect Prediction by Data Science and Machine Learning Approaches." International Journal of Advance Research, Ideas and Innovations in Technology 8.4 (2022). www.IJARIIT.com.
Abstract
The quality, dependability, and cost of maintenance are all significantly impacted by the existence of software flaws. Bug-free software, especially software that has been thoroughly built, is difficult to obtain because of the many hidden problems that have been found [7, 9]. A key issue for software technology is the creation of a model based on software bug prediction that can identify faulty components in the early stages of development. As a result, this is neither a linear or constant operation. PSO's formal foundations will be briefly discussed in the section that follows. A linear PSO allows the notion of margin maximization to be explained in an extremely easy manner since the score remains direct and constant number everywhere it works. The pattern of precision in graph analysis differs from that of accuracy. Two datasets, JM1 and KC1, show enhanced precision in the case of accuracy.