Prediction of software fault-prone classes using ensemble random forest with adaptive synthetic sampling algorithm

Balaram, A.; Vasundra, S.

doi:10.1007/s10515-021-00311-z

Cited by 40 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The suggested ensemble classifier solves the difficulties that existed in the previous approaches in the current study effort, which predicts the inherent errors in the program. Balaram [18] employed an intelligent strategy to forecast SFP by integrating ADASYN with E-RF to build the butterfly optimization algorithm (BOA) for identifying important characteristics. The BOA eliminates the problem of overfitting, while ADASYN addresses the issue of data imbalance for supplementary classes, resulting in a consistent data deformation mechanism.…”

Section: Related Research On Software Fault Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Software Fault Detection using Multi-Distinguished-Features Sampling with Ensemble Random Forest Classifier

2022

IJIES

View full text Add to dashboard Cite

Finding faults in software modules is an emerging issue in software reliability systems, and the assessment of the fault is performed by software fault prediction systems (SFPS). The identification process of fault-prone software modules is one of the prioritized aspects before initiating the testing process of the same modules. The SFPS helps improve software quality within the specified time and cost values. Early fault prediction in SFPS for the different software components showed significant results concerning the cost and time parameters. According to the state-ofthe-art SFPS, ensemble-based classifiers were performed best and most cost-effective compared to other classifier methods. Recently, a random ensemble forest with adaptive synthetic sampling (E-RF-ADASYN) has been developed, is tested on a sample of PROMISE datasets, and shown the cost-effective classifier results. In the logistic regression to software quality models, and the other knowledge of account for prior probability and costs of misclassification. Probabilities and costs of misclassification in a logistic regression-based classification algorithm for software quality modeling. The decision tree algorithm is an ensemble learning approach for prediction. The algorithm works based on developing several decision trees and later decides the output class based on the most popular one. The proposed work focuses on developing an alternative sampling method called ensemble-random forest with multi-distinguishedfeatures sampling (E-RF-MDFS), for obtaining the best sample illustration for representing the entire dataset. Batinduced butterfly optimization (BBO) has been used for the feature extraction process. The experiments are conducted on 8 datasets of the PROMISE database. The proposed E-RF-MDFS has improved performance than E-RF-ADASYN in fault detection accuracy, real positive rate, and Pearson's correlation coefficient. On comparing the performance of E-RF-based classifiers, the performance of the proposed MDFS is the best, with an FDA of 99.3 % (Xalan v2.6) than the ADASYN classifier.

show abstract

Section: Related Research On Software Fault Detectionmentioning

confidence: 99%

“…The main drawback of the method proposed in [18] is that Adaptative synthetic sampling delivers random data samples, and it cannot find the sample based on distinguishing features. Therefore, it sometimes fails to present the best sample illustration for large datasets.…”

Section: Related Research On Software Fault Detectionmentioning

confidence: 99%

Software Fault Detection using Multi-Distinguished-Features Sampling with Ensemble Random Forest Classifier

2022

IJIES

View full text Add to dashboard Cite

show abstract

“…It is the procedure of synthetic procedure that can be combined with adaptive boosting techniques for transforming and updating the weights to learn the best compensation for the data cases of skewed data distributions. For ensuring the best accuracy in the case of classification for minority and majority data classes, another classification algorithm Data Boost-IM algorithm is proposed by the respective author of [14], in which the examples of synthetic data are created for both minority and majority classes [15], [16] through the use of "seed" samples.…”

Section: Dataset Apply Mdfs Sample Datamentioning

confidence: 99%

Untitled

2022

INDJCSE

View full text Add to dashboard Cite

Finding faults in software modules is an emerging issue in software reliability systems and the assessment of the fault is performed by software fault prediction systems (SFPS). An identification process of faultprone of software modules is the most prioritized before initiating the testing process of the same modules. The SFPS helps to improve the quality of software within the specified time and cost values. Early fault prediction in SFPS for the different software components showed significant results concerning the cost and time parameters. According to the state-of-the-art of SFPS, ensemble-based classifiers were performed as the best and most cost-effective when compared to other classifier methods. An ensemble random forest with adaptive synthetic sampling (E-RF-ADASYN) is developed recently is tested on a sample of PROMISE datasets and shows the cost-effective classifier results. Our proposed work is focused on the development of another sampling method, say, Multi-Distinguished-Features Sampling (MDFS) for obtaining the best sample illustration for representing the entire dataset. The experiments are conducted on bench-marked PROMISE datasets for demonstrating the efficiency of the proposed MDFS-E-RF compared to other traditional methods.

show abstract

“…Suppose the property we want our program to satisfy is that the program executes four times in a loop. The ASK-CTL property is shown in Equation (7). Given the property, the variable involved in the property is a, so the tester adds a local area annotation ////-a or a wide area annotation ////-Package -ClassName -FunName -Deep -Int -a. in the program.…”

Section: Granularity Identificationmentioning

confidence: 99%

“…Software defect detection is an important means to ensure the reliability of concurrent software. There are kinds of research on software defect detection, including bug localisation [3,4], software fault prediction [5][6][7], error detection [8], and anomaly detection [9]. Researchers apply various techniques to detect software defects to ensure software reliability and correctness, and software model checking [10] is one of them.…”

Section: Introductionmentioning

confidence: 99%

Concurrent software fine‐coarse‐grained automatic modelling by Coloured Petri Nets for model checking

2022

View full text Add to dashboard Cite

The state space explosion restricts the error detection of concurrent software. The abstraction can provide a solution to avoid state space explosion, but it is easy to ignore important details, resulting in inaccurate detection results. This paper proposes a methodology of fine-coarse-grained automatic modelling for Java source programs. By the principle that the execution details of property-unchecked, non-interactive, and unrelated statements do not affect the model checking results, we model coarse-grained model fragments for such statements, while fine-grained model fragments for property-checked, interactive, and related statements. Our method reduces the model and state space and ensures the error detection of the source program based on model checking. Moreover, we prove the equivalence of the fine-grained model, the coarse-grained model, and the program. Finally, this paper gives an experiment to verify the effectiveness of the proposed method.

show abstract

Prediction of software fault-prone classes using ensemble random forest with adaptive synthetic sampling algorithm

Cited by 40 publications

References 20 publications

Software Fault Detection using Multi-Distinguished-Features Sampling with Ensemble Random Forest Classifier

Software Fault Detection using Multi-Distinguished-Features Sampling with Ensemble Random Forest Classifier

Untitled

Concurrent software fine‐coarse‐grained automatic modelling by Coloured Petri Nets for model checking

Contact Info

Product

Resources

About