International Journal of Advanced Networking and Applications

Maaz Rasheed Malik ¹, Liu Yining ¹, Salahuddin Shaikh ²

Affiliations
1 Dept. of Information Communication Engineering, Guilin University of Electronic Technology, Guilin, CN
2 School of Control & Computer Engineering, North China Electric Power University, Beijing, CN

Abstract

Many researchers have worked on the Software fault forecast model because the software fault forecast is very important in software development projects. In terms of the Software fault forecast model, earlier researchers have examined defective datasets models with the help of metrics and classification methods. Classification is assuming an exceptionally major job in the software fault forecast model, which is an important issue in data mining. The machine learning system as a finding way for the information securing or information extraction issue has examined it widely. The contribution to a classifier is a training data set of precedents, every one of which is labeled with a class name. Classification separates data tests into target classes. Software modules are categorized as defected models or not defected models by classification draws near. In Classification, class categories are known thus it is a supervised learning approach. In our research, software fault forecast datasets models are examined with the help of tree vector machine classification. Our proposed model is a tree vector machine, which is used for increasing the positive accuracy and efficiency of the software fault forecast model. We have used multiple tree classifiers for getting more accurate results and compare them with each other. During the analysis of the experiments, j48, random forest and random tree have increased their performance in accuracy as well as efficiency. However, the performance of REP Tree, Hoeffding Tree and Decision Stump is not so good at all measure rates. The experiment's analysis results showed that not every tree classifier could be good in all in measure unit.

Keywords

Software, Fault Forecast, Classification, Defect prone, Support Vector Machine, J48, Random Tree.

Full Text

   

Salahuddin Shaikh ¹, Liu Changan ¹, Maaz Rasheed Malik ²

Affiliations
1 School of Control & Computer Engineering, North China Electric Power University, Beijing, CN
2 Dept. of Information Communication Engineering, Guilin University of Electronic Technology, Guilin, CN

Abstract

The few researchers have put their ideas about class-imbalance during analysis of datasets, two types of class imbalances are present in datasets. First type in which some classes have many models than others and that is called between class imbalance. Second type in which few subsets of one class have less models than other subsets of similar class and that is within class-imbalance. Over-sampling and Under-sampling innovation assume noteworthy jobs in tackling the class-imbalance issue. There are numerous dissimilarities of over-sampling and under-sampling methods which utilized for class imbalanced dataset model. We have used two sampling techniques in our research paper for our imbalanced datasets models. One is over-sampling using SMOTE technique and another one is under-sampling using spread-sub-sample. During experiments, all results are measured in evaluation performance measure. Mostly they all are class imbalanced measurements, in which precision, recall, f-measure, area under curve and 12 different classifiers we have used in our experiments to get the comparatively results of both sampling techniques. The over-all analysis showed that the efficiency of correctly classified in over-sampling techniques is enhanced in few classifiers as compared to under-sampling techniques. The TP-rate and positive accuracy of both techniques, the stacking is worst classifier in these experiments and multi classification and LMT couldn’t increase the TP-rate in under-sampling techniques. The over-all comparative analysis of both techniques as compared with without using sample techniques have increased but over-sampling technique is more valuable to use for solving the class imbalance issue.

Keywords

- Software prediction, Under-sampling, Over-sampling, Sampling, Class imbalance, Defect-Prone.

Full Text