English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Code Smell, similar to a bad smell, is a surface indication of somethingtainted but in terms of software writing practices. This metric is anindication of a deeper problem lies within the code and is associated with anissue which is prominent to experienced software developers with acceptablecoding practices. Recent studies have often observed that codes having codesmells are often prone to a higher probability of change in the softwaredevelopment cycle. In this paper, we developed code smell prediction modelswith the help of features extracted from source code to predict eight types ofcode smell. Our work also presents the application of data sampling techniquesto handle class imbalance problem and feature selection techniques to findrelevant feature sets. Previous studies had made use of techniques such asNaive - Bayes and Random forest but had not explored deep learning methods topredict code smell. A total of 576 distinct Deep Learning models were trainedusing the features and datasets mentioned above. The study concluded that thedeep learning models which used data from Synthetic Minority OversamplingTechnique gave better results in terms of accuracy, AUC with the accuracy ofsome models improving from 88.47 to 96.84.

An Empirical Study on Predictability of Software Code Smell Using Deep Learning Models