Scholarlink

<p>Software development is based on explicit technical fundamentals and techniques. There are diverse phases executed to predict the defects in software, such as employing the data for input, pre-processing it, extracting the attributes, and classifying the defect. The given paper introduces an ensemble framework that comprises algorithms, namely Gaussian Naive Bayes (GNB), Bernoulli Naïve Bayes (BNB), Random Forest (RF), and Support Vector Machine (SVM), for predicting the software defects. This ensemble approach consists of Principal Component Analysis (PCA) or orthogonal linear transformation (OLT) with class balancing for feature selection. Python is executed for simulating the proposed model. In addition to this, the performance of the proposed work is validated and compared with existing recent studies based on evaluation metrics such as accuracy, precision and recall. The results show that the proposed framework outperforms the existing recent studies in terms of performance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Ensemble Voting classification Approach for Software defects prediction

  • 期刊论文

  • 发表日期：

    2025年1月15日

查看全文
  • Ashu Mehta,
  • Navdeep Kaur,
  • Amandeep Kaur

摘要

Software development is based on explicit technical fundamentals and techniques. There are diverse phases executed to predict the defects in software, such as employing the data for input, pre-processing it, extracting the attributes, and classifying the defect. The given paper introduces an ensemble framework that comprises algorithms, namely Gaussian Naive Bayes (GNB), Bernoulli Naïve Bayes (BNB), Random Forest (RF), and Support Vector Machine (SVM), for predicting the software defects. This ensemble approach consists of Principal Component Analysis (PCA) or orthogonal linear transformation (OLT) with class balancing for feature selection. Python is executed for simulating the proposed model. In addition to this, the performance of the proposed work is validated and compared with existing recent studies based on evaluation metrics such as accuracy, precision and recall. The results show that the proposed framework outperforms the existing recent studies in terms of performance.