The design of polynomial function-based neural network predictors for detection of software defects

Park, Byoung-Jun; Oh, Sung‐Kwun; Pedrycz, Witold

doi:10.1016/j.ins.2011.01.026

Cited by 58 publications

(28 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Fig 4, the design of polynomial function-based neural network predictors for detection of software defects [10] claims that the polynomial function-based neural networks (pf-NNs) used with weighted cost function provides the lower accuracy 80.3% and 78.8% for linear function-based neural network (lf-NN) and quadratic function-based neural network (qf-NN) respectively.…”

Section: Results and Comparisonmentioning

confidence: 99%

“…They compare the results with radial basis function (RBF) NNs. In their study, pf-NNs used with standard cost function provides the high accuracy (96.1%) but low probability of detection (66.7 or 63.3%) and pf-NNs used with weighted cost function provides the lower accuracy 80.3% and 78.8% but higher probability of detection 93.3% and 96.7% for lf-NN and qf-NN, respectively [10].…”

Section: Review Of Literaturementioning

confidence: 96%

See 1 more Smart Citation

Software Defect Prediction Tool based on Neural Network

Singh¹,

Salaria²

2013

IJCA

View full text Add to dashboard Cite

There has been a tremendous growth in the demand for software fault prediction during recent years. In this paper, Levenberg-Marquardt (LM) algorithm based neural network tool is used for the prediction of software defects at an early stage of the software development life cycle. It helps to minimize the cost of testing which minimizes the cost of the project. The methods, metrics and datasets are used to find the fault proneness of the software. The study used data collected from the PROMISE repository of empirical software engineering data. This dataset uses the CK (Chidamber and Kemerer) OO (object-oriented) metrics. The accuracy of Levenberg-Marquardt (LM) algorithm based neural network are comparing with the polynomial function-based neural network predictors for detection of software defects. Our results indicate that the prediction model has a high accuracy. General TermsSoftware defect prediction

show abstract

Section: Results and Comparisonmentioning

confidence: 99%

Section: Review Of Literaturementioning

confidence: 96%

Software Defect Prediction Tool based on Neural Network

Singh¹,

Salaria²

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…The second class that have an rich amount of occurrences. Identifying the minority classes is important in various fields such as medicinal analysis [9], software faults detection [10], Finances [11], drug discovery [11] or bio-informatics [12]. The classical learning techniques are not adapted to imbalanced data sets.…”

Section: Imbalanced Big Datamentioning

confidence: 99%

Parallel processing on Big Data in the context of Machine Learning and Hadoop Ecosystem: A Survey

Brahmane¹,

R²

2018

IJET

View full text Add to dashboard Cite

Emergent Big Data applications have become gradually more essential. In reality, a lot of institutes, businesses and in general entire society from diverse segments depend more and more on information take out from enormous quantity of raw information, statistics and numbers. On the other hand, in Big Data perspective, customary information methods and policies are not as much of capable. They prove a time-consuming receptiveness and are short of quantifiability, measurability, presentation and accurateness. To solve the composite Big Data constraints and difficulties, a large amount effort has been carried out. As an effect, different categories of packages, distributions and technologies have been developed. In this paper an evaluation is done, this studies recent technologies developed for Big Data. It aims to assist to choose and adopt the exact combination of diverse Big Data technologies according to their technological, scientific needs and particular applications requirements. It provides not only a worldwide sight of most important Big Data technologies but also relationship according to special organizational, classifications levels

show abstract

“…The process of defect prediction has been utilizing various machine learning approaches including Logistic Regression [6], Decision Trees [7], Neural Networks [8] and Naive-Bayes [9]. The two important data quality aspects such as class imbalance and noisy data set attributes [10] generally influence the performance of classification.…”

Section: Introductionmentioning

confidence: 99%