Scribd
Upload
22 views1 page

Majorproject Abstract

This project presents a novel approach to improve software defect prediction accuracy using machine learning techniques. It emphasizes the importance of feature selection to enhance model performance, evaluated on five NASA datasets using various algorithms. The findings indicate that incorporating feature selection leads to higher accuracy in predicting software defects compared to models that do not utilize it.

Uploaded by

ayyoruaravind
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
22 views1 page

Majorproject Abstract

This project presents a novel approach to improve software defect prediction accuracy using machine learning techniques. It emphasizes the importance of feature selection to enhance model performance, evaluated on five NASA datasets using various algorithms. The findings indicate that incorporating feature selection leads to higher accuracy in predicting software defects compared to models that do not utilize it.

Uploaded by

ayyoruaravind
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

A NOVEL APPROACH TO IMPROVE SOFTWARE DEFECT

PREDICTION ACCURACY USING MACHINE LEARNING

ABSTRACT
Software defect prediction helps find errors in the source code before the testing phase begins.
This plays an important role in improving the quality and success of software. This project
focuses on predicting software defects to identify errors in source code before the testing phase,
which helps improve software quality and reliability. Commonly used techniques for defect
prediction include clustering, statistical methods, machine learning, black box and white box
testing, and neural networks. To improve prediction accuracy, this project applies feature
selection, which helps machine learning models by selecting the most important features from
the data. The performance is evaluated using five publicly available NASA datasets: CM1,
JM1, KC2, KC1, and PC1.Various machine learning algorithms are used in this project,
includingRandomForest,LogisticRegression,MultilayerPerceptron,BayesianNet,RuleZeroR,J48,
LazyIBK, Support Vector Machine, Neural Networks, and Decision Stump. The WEKA tool is
used for data preprocessing and classifierimplementation, and Minitab is used for statistical
analysis. The results show that this project achieves higher accuracy in defect prediction when
feature selection is used, compared to models without feature selection.
Guide Batch-1:
Dr. Khaja Ziauddin 1.Ganji Arpitha (HT.NO:21N01A0540)
Associate Professor & HOD 2.Gaddam Sai Manideep(HT.NO:21N01A0537)
Department of CSE 3.Gajarla Alekya (HT.NO:21N01A0538)

You might also like