Deep Learning Based Code Smell Detection

Liu, Hui; Jin, Jiahao; Xu, Zhi-Feng; Zou, Yanzhen; Bu, Yifan; Zhang, Lu

doi:10.1109/tse.2019.2936376

Cited by 69 publications

(64 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other techniques, such as the memory consistency model, graph transformation, behavior protection and type constraints (Liu et al, 2020; Tip, 2011), can be used to validate the consistency. Though some works have been performed, consistency validation for concurrency-oriented refactoring still needs more efforts.…”

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

“…More code smell will be detected, and then refactoring opportunities will be recommended to the developers. Intelligent refactoring tools (Liu et al, 2020) will be developed to assist concurrent programming in improving performance. More efforts will be given to developing consistency validation techniques for concurrency-oriented software refactoring (Max et al, 2010).…”

Section: Future Trendsmentioning

confidence: 99%

See 2 more Smart Citations

A survey of concurrency-oriented refactoring

Zhang

2020

Concurrent Engineering

View full text Add to dashboard Cite

Refactoring has become an effective approach to convert sequential programs into concurrent programs. Many refactoring algorithms and tools are proposed to assist developers in writing high-performance concurrent programs. Although researchers actively conduct surveys on refactoring, we are not aware of any survey that summarizes, categorizes and discusses concurrency-oriented refactoring. To this end, this paper presents a survey that investigates how refactoring assists with concurrent programming. To the best of our knowledge, this paper is the first survey that summarizes the state-of-the-art, concurrency-oriented refactoring. First, we design six research questions addressing the concurrent structure, programming language, performance improvement and consistency evaluation. Second, we answer these questions by examining the related papers and then present the results to show how refactoring provides support for concurrent programming after a decade of development, such as transforming the concurrent structures, supporting parallel language, and improving performance. Finally, we summarize the related works and present the future trends.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Future Trendsmentioning

confidence: 99%

See 1 more Smart Citation

A survey of concurrency-oriented refactoring

Zhang

2020

Concurrent Engineering

View full text Add to dashboard Cite

show abstract

“…Finally, this network outputs each RoI of the softmax probabilities and bounding-box regression coordinates of each class. 23 We utilize the Faster R-CNN to detect UI components in our approach.…”

Section: Cnnmentioning

confidence: 99%

“…Table 2 shows a list of hyper-parameters of UI component detector. The fine-tuning of these hyper-parameters are all on the basis of a Keras implementation 23 of Faster R-CNN 17 along with the empirical knowledge. In Table 2, the first column represents the name of hyper-parameters, the second column lists the value of hyper-parameters, and the last column lists a description of these hyper-parameters.…”

Section: Ui Component Detector Trainingmentioning

confidence: 99%

image2emmet: Automatic code generation from web user interface image

Sun

et al. 2021

J Software Evolu Process

View full text Add to dashboard Cite

Web development usually follows with analyzing the functionality, designing the user interface (UI) prototype, implementing the UI by front-end (FE) developers and implementing the REpresentational State Transfer (RESTful) application programming interface (API) by back-end (BE) programmers. Unfortunately, web development is a tedious, cumbersome, and time-consuming task, which makes it a challenge for the FE programmers to work in an efficient way. In this paper, we propose an approach, image2emmet, to assist FE programmers in implementing the UI. First, we collect HyperText Markup Language, Cascading Style Sheets (HTML-CSS) dataset in an automatic and efficient way. The HTML-CSS dataset used for model training consists of HTML-CSS code and its display images. Second, the faster region-based convolutional neural network (CNN) (R-CNN) is utilized to detect the UI component. Finally, we build a model combining CNN and long short-term memory (LSTM) to transform the UI component into the HTML-CSS code. The empirical study demonstrates that image2emmet can achieve a precision of 80% on the UI component detection and 60% on the transformation of UI component into HTML-CSS code. K E Y W O R D S code generation, HTML-CSS code, UI component, web development | INTRODUCTIONNowadays, there are over 1.2 billion websites 1 on the world wide web. [1][2][3] Websites are available in almost every field of the blog, business, brochure, crowdfunding, e-commerce, education, media or entertainment, and so on. A nice user interface (UI) of the website can attract people and allow them to conveniently find the information they need. The development steps of the website in recent years follow with analyzing the functionality, designing the UI prototype, implementing the UI by front-end (FE) developers, and implementing the RESTful (REpresentational State Transfer) application programming interface (API) by back-end (BE) programmers. 4 Besides, FE web development is a practice of producing HTML, CSS, and JS (JavaScript) files for a website. Once the designers finish designing a UI prototype, FE developers need to implement the UI via various tools or libraries such as Semantic UI. 2 Unfortunately, the procedure of implementing the UI is a tedious, cumbersome, and timeconsuming task and makes it a challenge for the FE programmers to work in an uneconomical way.

show abstract

MARS: Detecting brain class/method code smell based on metric–attention mechanism and residual network

Zhang

Dong

2021

J Software Evolu Process

View full text Add to dashboard Cite

Code smell is the structural design defect that makes programs difficult to understand, maintain, and evolve. Existing works of code smell detection mainly focus on prevalent code smells, such as feature envy, god class, and long method. Few works have been done on detecting brain class/method. Furthermore, existing deep‐learning‐based approaches leverage the CNN model to improve accuracy by barely increasing the number of layers, which may cause a problem of gradient degradation. To this end, this paper proposes a novel approach called MARS to detect brain class/method. MARS improves the gradient degradation by employing an improved residual network. It increases the weight value of those important code metrics to label smelly samples by introducing a metric–attention mechanism. To support the training of MARS, a dataset called BrainCode is generated by extracting more than 270,000 samples from 20 real‐world applications. MARS is evaluated on BrainCode and compared to other machine‐learning‐based and deep‐learning‐based approaches. The experimental results demonstrate that the average accuracy of MARS is 2.01 % higher than that of the existing approaches, which improves state‐of‐the‐art.

show abstract

Deep Learning Based Code Smell Detection

Cited by 69 publications

References 58 publications

A survey of concurrency-oriented refactoring

A survey of concurrency-oriented refactoring

image2emmet: Automatic code generation from web user interface image

MARS: Detecting brain class/method code smell based on metric–attention mechanism and residual network

Contact Info

Product

Resources

About