International Conference on Computer and Knowledge Engineering

Home / 12th International Conference on Computer and Knowledge Engineering

Cross-project Defect Prediction with An Enhanced Transfer Boosting Algorithm

Authors :

Nazgol Nikravesh¹ Mohammad Reza Keyvanpour²

1- Data Mining Laboratory, Department of Computer Engineering, Faculty of Engineering, , Alzahra University, Tehran, Iran 2- Department of Computer Engineering, Faculty of Engineering, Alzahra University, Tehran, Iran

Keywords :

class imbalance،software defect prediction،cross-project defect prediction،transfer learning،training data selection

Abstract :

A growing number of software projects makes it increasingly crucial to predict software defects. If sufficient historical data is available, within-project defect prediction models can be effective. During the early stages of software development, however, insufficient data exists to train an effective predictor. Cross-project defect prediction (CPDP) uses information from previous mature projects (source data) to predict whether new software modules (target data) will be defective. CPDP models must take into account the fact that data distributions between target and source projects are different. These models often reduce distribution differences by either selecting training data or using transfer learning methods. Using transfer learning effectively reduces distribution differences in recent CPDP models. Yet none of them have taken into account the possibility that negative transfer may occur as a result of imbalanced nature of defect data. In this paper, a four-step model is proposed, of which three steps are dedicated to the preparation of training data and their initial weights for using in the fourth step, which involves an enhanced version of the transfer boosting algorithm. In this algorithm imbalance nature of data is considered and the weighting of the source data is updated to enhance the prediction performance. Therefore, aside from reducing distribution differences between source and target data, the model also addresses issues related to defect data class imbalance. As compared to four state-of-the-art CPDP models, this model provided consistent and accurate predictions for fifteen projects from PROMISE, AEEEM, and SOFTLAB. Our proposed model provided the best average results for both AUC and F-measure and in some datasets, the improvements were more than 5%.

Papers List

List of archived papers

Deep Learning-Based Malaysian Sign Language (MSL) Recognition: Exploring the Impact of Color Spaces

Ervin Gubin Moung - Precilla Fiona Suwek - Maisarah Mohd Sufian - Valentino Liaw - Ali Farzamnia - Wei Leong Khong

Sports News Summarization Using Ensebmle Learning

Moein Sartakhti.salimi@gmail.com - Mohammad Javad Maleki Kahaki - Ahmad Yoosofan - Seyyed Vahid Moravvej

Load Frequency Control of Geothermal Power Plant Incorporated Two-Area Hydro-Thermal System with AC-DC Lines

Shanker J Gambhire - Malligunta Kiran Kumar - Hossein Shahinzadeh - Mohammad-hossein Fayaz-dastgerdi - B. Srikanth Goud - Ch.Naga sai Kalyan

Segmentation of Hard Exudates in Retinal Fundus Images Using BCDU-Net

Nafise Ameri - Nasser Shoeibi - Mojtaba Abrishami

Adversarial Robustness Evaluation with Separation Index

Bahareh Kaviani Baghbaderani - Afsaneh Hasanebrahimi - Ahmad Kalhor - Reshad Hosseini

African Vultures Optimization Algorithm for Optimal Damping Controllers Design in the Electrical Power Grid System

Aliyu Sabo - Theophilus Ebuka Odoh - Samuel Habu - Hossein Shahinzadeh - Farshad Ebrahimi

Semi-Supervised Supply Chain Fraud Detection with Unsupervised Pre-Filtering

Fatemeh Moradi - Mehran Tarif - Mohammadhossein Homaei

Lempel-Ziv-based Hyper-Heuristic Solution for Longest Common Subsequence Problem

Mahdi Nasrollahi - Reza Shami Tanha - Mohsen Hooshmand

Iris Detection and Segmentation Using Deep Learning

Ali Khaki - Ali Aghagolzadeh - Bagher Rahimpour Cami

No-Reference Video Quality Assessment by Deep Feature Maps Relations

Amir Hossein Bakhtiari - Azadeh Mansouri