A Study on the Metrics-Based Duplicated Code Type Smell Detection Techniques Relating the Metrics to Its Quality

Gupta, Aditi; Goyal, Rinkaj

doi:10.1007/978-981-19-4960-9_41

Cited by 1 publication

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Type-1 (T1) refers to code fragments with the same syntax except for comments and white spaces [4]. Type-2 (T2) corresponds to code fragments with the same grammatical structure but different identifiers, constants, and types [5]. Type-3 (T3) represents code fragments that have undergone modifications after copying, such as changing, adding, or deleting a few statements [6].…”

Section: Related Work a Code Clone Detectionmentioning

confidence: 99%

Code Clone Detection via Software Visualization Representation Learning

Qiu,

Wang,

Liang

et al. 2023

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

Code clone detection technology aims to automatically detect code similarity and help developers identify and reduce code duplication. While code syntax analysis-based methods are commonly used for clone detection, they may not capture semantic information due to bypassing the analysis of code text. To address this issue, this paper proposes a new method called visualization representation learning for code clone detection (VRL4CCD). This method converts source code fragments into grayscale images to preserve textual information and then utilizes VGG16 and a self-attention mechanism to extract features related to code semantic similarity. A siamese neural network is used to learn the similarity pattern between code features. Experimental results on the Big Clone Bench and Google Code Jam datasets demonstrate that VRL4CCD outperforms current clone detection methods regarding precision, recall, and F1-score, indicating the effectiveness of code visualization technology in clone detection tasks.

show abstract

Section: Related Work a Code Clone Detectionmentioning

confidence: 99%