Improved mayfly optimization deep stacked sparse auto encoder feature selection scorched gradient descent driven dropout <scp>XLM</scp> learning framework for software defect prediction

Anbu, M.

doi:10.1002/cpe.7240

Cited by 2 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 3 ], authors have balanced datasets to get good results. The [ 4 ] used optimization, feature selection, dropout, and autoencoder concepts, but still, there are possibilities of non-guarantee on parameter settings and convergence. Plus, the whole thing is costlier to train due to using a complex data model that can add up the cost.…”

Section: Introductionmentioning

confidence: 99%

A trustworthy hybrid model for transparent software defect prediction: SPAM-XAI

Mustaqeem,

Mustajab,

Alam

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Maintaining quality in software development projects is becoming very difficult because the complexity of modules in the software is growing exponentially. Software defects are the primary concern, and software defect prediction (SDP) plays a crucial role in detecting faulty modules early and planning effective testing to reduce maintenance costs. However, SDP faces challenges like imbalanced data, high-dimensional features, model overfitting, and outliers. Moreover, traditional SDP models lack transparency and interpretability, which impacts stakeholder confidence in the Software Development Life Cycle (SDLC). We propose SPAM-XAI, a hybrid model integrating novel sampling, feature selection, and eXplainable-AI (XAI) algorithms to address these challenges. The SPAM-XAI model reduces features, optimizes the model, and reduces time and space complexity, enhancing its robustness. The SPAM-XAI model exhibited improved performance after experimenting with the NASA PROMISE repository’s datasets. It achieved an accuracy of 98.13% on CM1, 96.00% on PC1, and 98.65% on PC2, surpassing previous state-of-the-art and baseline models with other evaluation matrices enhancement compared to existing methods. The SPAM-XAI model increases transparency and facilitates understanding of the interaction between features and error status, enabling coherent and comprehensible predictions. This enhancement optimizes the decision-making process and enhances the model’s trustworthiness in the SDLC.

show abstract

Section: Introductionmentioning

confidence: 99%

A trustworthy hybrid model for transparent software defect prediction: SPAM-XAI

Mustaqeem,

Mustajab,

Alam

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

Application of Big Data Visualization Technology in Quality Assessment of English Translation of Ancient Books

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

The development and application of machine translation cannot be separated from the evaluation of its quality. Correct evaluation is a correct lead to its development direction, and the translation direction respected by mainstream evaluation can be said to be the development direction of machine translation in research. In this paper, the Transformer model of the multi-head attention mechanism is constructed, and the optimization and improvement schemes in both model architecture and training data are proposed for the mBERT and XLM models to form the XLM-R model. Based on the predictor-evaluator QE model and the pre-trained model-evaluator QE two models, the XLM-R translation quality assessment baseline is proposed. A CLS pooling method is proposed for the baseline system, which ensures similarity at a finer-grained subword level. Meanwhile, the subword similarity scoring index is embodied using a simple splicing method, taking into account the global semantic quality. Simulation experiments are set up to evaluate the quality of translation tasks at the sentence and system levels, respectively. There was a 7.92% improvement in the Pearson correlation coefficient of the model with similarity characterization when compared to the one without the model in the sentence-level QE task development set, which was 0.0379 higher. The model’s translation fluency also showed an increasing trend in the interval of 0.15 to 0.5 with the growth of the manual score, indicating that the model proposed in this paper is effective in baseline system evaluation.

show abstract

Improved mayfly optimization deep stacked sparse auto encoder feature selection scorched gradient descent driven dropout XLM learning framework for software defect prediction

Cited by 2 publications

References 33 publications

A trustworthy hybrid model for transparent software defect prediction: SPAM-XAI

A trustworthy hybrid model for transparent software defect prediction: SPAM-XAI

Application of Big Data Visualization Technology in Quality Assessment of English Translation of Ancient Books

Contact Info

Product

Resources

About