A systematic literature review on the use of machine learning in code clone research

Kaur, Manpreet; Rattan, Dhavleesh

doi:10.1016/j.cosrev.2022.100528

Cited by 7 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the limited number of studies (only 20), and heterogeneous nature of the majority, the application of meta-analysis is infeasible. Instead, we have opted for a descriptive synthesis analysis approach, as outlined in reference [69], which was also utilized in other relevant studies [6,14,15,17,19].…”

Section: Plos Onementioning

confidence: 99%

“…Recent breakthroughs in machine learning (ML), particularly within the domains of language modeling [10], machine translation [11], speech recognition [12], and online handwritten [13], have sparked interest of researcher in leveraging ML algorithms for the detection of both syntactic and semantic clones. A diverse array of techniques have been applied to learn distinct patterns that distinguish clones from non-clones, even across different clone categories [14,15]. Deep learning (DL) techniques, like recurrent neural networks (RNNs), graph neural networks (GNN), and others have proven effective in capturing both syntactic and semantic clones [14].…”

Section: Introductionmentioning

confidence: 99%

“…They reviewed recent DL techniques, analyzing their effectiveness, complexity, and scalability, and addressing associated challenges and limitations. Kaur and Rattan [15] presented a systematic review of ML techniques in code clone detection up to 2020, providing insights into clone types, metrics, datasets, code representation, and tools. Morteza et al [19] conducted a systematic review on code similarity measurement and clone detection, offering insights into the current techniques, applications, and challenges.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A systematic literature review on the applications of recurrent neural networks in code clone research

Quradaa,

Shahzad,

Almoqbily

2024

PLoS ONE

View full text Add to dashboard Cite

Code clones, referring to code fragments that are either similar or identical and are copied and pasted within software systems, have negative effects on both software quality and maintenance. The objective of this work is to systematically review and analyze recurrent neural network techniques used to detect code clones to shed light on the current techniques and offer valuable knowledge to the research community. Upon applying the review protocol, we have successfully identified 20 primary studies within this field from a total of 2099 studies. A deep investigation of these studies reveals that nine recurrent neural network techniques have been utilized for code clone detection, with a notable preference for LSTM techniques. These techniques have demonstrated their efficacy in detecting both syntactic and semantic clones, often utilizing abstract syntax trees for source code representation. Moreover, we observed that most studies applied evaluation metrics like F-score, precision, and recall. Additionally, these studies frequently utilized datasets extracted from open-source systems coded in Java and C programming languages. Notably, the Graph-LSTM technique exhibited superior performance. PyTorch and TensorFlow emerged as popular tools for implementing RNN models. To advance code clone detection research, further exploration of techniques like parallel LSTM, sentence-level LSTM, and Tree-Structured GRU is imperative. In addition, more research is needed to investigate the capabilities of the recurrent neural network techniques for identifying semantic clones across different programming languages and binary codes. The development of standardized benchmarks for languages like Python, Scratch, and C#, along with cross-language comparisons, is essential. Therefore, the utilization of recurrent neural network techniques for clone identification is a promising area that demands further research.

show abstract

Section: Plos Onementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A systematic literature review on the applications of recurrent neural networks in code clone research

Quradaa,

Shahzad,

Almoqbily

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The obtained results demonstrate success in detecting similarity, based on different "collocation-based" and "dependency-based" features as well as topic modelling. The most recent reviews in the field may be found in [45][46][47].…”

Section: Using Machine Learning and Clustering Techniquesmentioning

confidence: 99%

Assembly Function Recognition in Embedded Systems as an Optimization Problem

Avitan,

Ravve,

Volkovich

2024

Mathematics

View full text Add to dashboard Cite

Many different aspects of software system development and verification rely on precise function identification in binary code. Recognition of the source Assembly functions in embedded systems is one of the fundamental challenges in binary program analysis. While numerous approaches assume that the functions are given a priori, correct identification of the functions in binaries remains a great issue. This contribution addresses the problem of uncertainty in binary code in identification of functions, which were optimized during compilation. This paper investigates the difference between debug and optimized functions via modeling of these functions. To do so, we introduce an extensible model-centred hands-on approach for examining similarities between binary functions. The main idea is to model each function using a set of predetermined, experimentally discovered features, and then find a suitable weight vector that could give impact factor to each such a feature. After finding the weight vector, the introduced models of such desired functions can be identified in binary software packages. It means that we reduce the similarity identification problem of the models to a classical version of optimization problems with one optimization criterion. Using our implementation, we found that the proposed approach works smoothly for functions, which contain at least ten Assembly instructions. Our tool guarantees success at a very high level.

show abstract

“…The definition of synchronous motion of multiple axes states that each axis must traverse the distance of each segment by a position command at the same time. It is a great challenge to maintain synchronous motion in complex machining of freeform surfaces [29][30][31]. In the case of the assumption that a curved surface consists of different small curvature segments with different normal vectors, machining such a surface is complicated.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Finishing Milling Strategies Using Topography of the Machined Surface

Varga

Ižol²,

Kaščák³

et al. 2023

Acta Metall Slovaca

View full text Add to dashboard Cite

The plastics processing and injection molding industry is known for the fact that the future molded part contains a variety of geometric shapes and, in some cases, free surfaces. To produce these shapes, knowledge of CAM systems is required to enable the programmer to select the necessary milling strategies designed to achieve the best possible quality and dimensional accuracy. However, it is equally necessary to understand and appreciate the effect of each strategy and which strategy is best suited for a given type of surface. The paper compares finishing milling strategies by evaluating the topography of the machined surface. The material was AlCu4Mg aluminium alloy, where Constant-Z and Spiral strategy – circle-type finishing strategies were selected for the production process. Surface topography analysis was evaluated and compared at three different heights of the produced part with respect to the tool contact with the machined surface, which showed a variation in toolpaths and therefore also in the quality of machining. The surface topography results demonstrated the Constant Z strategy to be the more suitable strategy for producing the shaped surface, which achieved uniform toolpaths over the whole height of the part.

show abstract

A systematic literature review on the use of machine learning in code clone research

Cited by 7 publications

References 34 publications

A systematic literature review on the applications of recurrent neural networks in code clone research

A systematic literature review on the applications of recurrent neural networks in code clone research

Assembly Function Recognition in Embedded Systems as an Optimization Problem

Comparison of Finishing Milling Strategies Using Topography of the Machined Surface

Contact Info

Product

Resources

About