Predicting Code Smells and Analysis of Predictions: Using Machine Learning Techniques and Software Metrics

Mhawish, Mohammad Y.; Gupta, Manjari

doi:10.1007/s11390-020-0323-7

Cited by 42 publications

(38 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nucci et al [62] obtained accuracy approximately 83.00% using Random forest and J48 algorithm. Mhawish et al [36] obtained highest accuracy 98.48% using GBT model.…”

Section: Impact Of 10-cross Validation and Grid Searchmentioning

confidence: 95%

“…Nucci et al [62] obtained approximately 82.00% using Random forest and J48 algorithm. Mhawish et al [36] obtained highest accuracy 95.97% using Random forest model. Guggulothu et al [37] obtained best accuracy 95.90% using Random forest algorithm…”

Section: Impact Of 10-cross Validation and Grid Searchmentioning

confidence: 95%

“…Mhawish et al [36] suggested code smells analysis of Predictions using machine learning techniques and software metrics. They also applied genetic algorithm-based feature selection methods to enhance the accuracy of these machine learning algorithms by selecting the best features in each dataset.…”

Section: Related Workmentioning

confidence: 99%

“…The best parameter for each algorithm is different, depending on training data set. To determine the correct parameters' values, different combination of parameter values for each algorithm should be tested; so that the prediction model can correctly predict the test data set [36].…”

Section: E Parameter Optimizationmentioning

confidence: 99%

See 3 more Smart Citations

A Novel Approach for Code Smell Detection: An Empirical Study

Dewangan

Rao

Mishra³

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nucci et al [62] obtained accuracy approximately 83.00% using Random forest and J48 algorithm. Mhawish et al [36] obtained highest accuracy 98.48% using GBT model.…”

Section: Impact Of 10-cross Validation and Grid Searchmentioning

confidence: 95%

Section: Impact Of 10-cross Validation and Grid Searchmentioning

confidence: 95%

Section: Related Workmentioning

confidence: 99%

Section: E Parameter Optimizationmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Approach for Code Smell Detection: An Empirical Study

Dewangan

Rao

Mishra³

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…In some of the design pattern detection techniques UML diagrams are likewise utilized [9], [10]. In recent years, Machine learning is also being used in design patterns detection and similar problems [11], [12].…”

Section: Related Workmentioning

confidence: 99%

Design Patterns Discovery in Source Code: Novel Technique Using Substring Match

Pande¹,

Pant²,

Gupta³

et al. 2021

TEM Journal

Self Cite

View full text Add to dashboard Cite

The role of design pattern mining is a very significant strategy of re-engineering as with the help of detection one could easily understand complex systems. Of course, identifying a design pattern is not always a simple task. Additionally, pattern recovering methods often encounter problems dealing with space outburst for extensive systems. This paper introduces a new way to discover a design pattern based on an Impact Analysis matrix followed by substring match. UML diagrams corresponding to codes are created using Visual Paradigm Enterprise. Impact Analysis matrices of these UML diagrams are converted to string format. Considering system code string as main string and design pattern string as a substring, the main string is further decomposed. A substring match technique is developed here to discover design patterns in the source code. Overall, this procedure has the potential to convert the representation of system design and design pattern in ingenious shapes. In addition, this method has the advantage of moderation in the size. Therefore, this approach is beneficial for Software professionals and researchers due to its simplicity.

show abstract

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

Anbu

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Software testing is the process of improving software quality by classifying and removing defects in the software development. Previously, several methods were used for software defect prediction, but any one method did not provide sufficient accuracy. To overcome this issue, an improved may fly optimization with deep stacked sparse auto encoder feature selection scorched gradient descent driven dropout extreme learning machine framework (SDP‐IMFOFS‐GDDDXLMC) is proposed in this article for software defect prediction. Here, an IMFO method is considered for feature selection techniques. In feature selection technique, features are selected, such as PC1, PC4, and MC1 for selecting the probable minimal attribute. Then, GDDDXLMC approach is used to classify buggy and clean software detection. The proposed approach is implemented in MATLAB platform. The performance metrics, such as accuracy, precision, F‐measure, sensitivity, specificity, Mathew correlation coefficient (MCC) is examined to examine the performance of the proposed method. The simulation performance of the proposed SDP‐IMFOFS‐GDDDXLMC method attains higher accuracy 99.75%, 97.85%, 95.13%, 14.89%, 16.34%, 17.89%, and 98.79, higher sensitivity 96.34%, 91.23%, 89.12%, 12.67%, 17.56%, 18.90%, and 87.25% higher specificity 14.89%, 16.89%, 20.67%, 93.67%, 92.37%, 98.47%, and 94.78% compared with the existing methods, like SDP‐MLP‐PSO, SDP‐BPNN‐RBFNN, SDP‐CNN‐RNN‐LSTM, SDP‐KBN‐LIME, SDP‐SLDeep‐LSTM, SDP‐K‐PCA‐ELM, and SDP‐CNN‐PHI forest, respectively.

show abstract

Predicting Code Smells and Analysis of Predictions: Using Machine Learning Techniques and Software Metrics

Cited by 42 publications

References 54 publications

A Novel Approach for Code Smell Detection: An Empirical Study

A Novel Approach for Code Smell Detection: An Empirical Study

Design Patterns Discovery in Source Code: Novel Technique Using Substring Match

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

Contact Info

Product

Resources

About