Shaima Ebraheem Hejres, Mustafa Hammad · IET conference proceedings. · 2022
Code smells are indications of design issues in software. The importance of early detection of these indicators helps in improving the maintenance process and raising the efficiency of software work. Besides detecting the severity of code smells the big problems of refactoring can be avoided as well. Machine learning algorithms are an effective way to detect code smells. This paper explicitly examines three different algorithms for SMO, ANN, and J48, among the four, most frequently detected code smells such as data class, god class, feature envy, and along method. The results showed that the SMO algorithm got better accuracy for data class, god class, and feature envy. Apart from this, ANNE with SMO algorithms got identical higher accuracy results in the long method.
Cited by 3
Hlib Babii, Andrea Janes, Romain Robbes · arXiv (Cornell University) · 2019
When building machine learning models that operate on source code, several decisions have to be made to model source-code vocabulary. These decisions can have a large impact: some can lead to not being able to train models at all, others significantly affect performance, particularly for Neural Language Models. Yet, these decisions are not often fully described. This paper lists important modeling choices for source code vocabulary, and explores their impact on the resulting vocabulary on a large-scale corpus of 14,436 projects. We show that a subset of decisions have decisive characteristics, allowing to train accurate Neural Language Models quickly on a large corpus of 10,106 projects.
Cited by 25Open access
Li, Lejin, Zhang, Xiao-Yi, Tang, Shuncheng et al. · Zenodo (CERN European Organization for Nuclear Research) · 2025
The source code of the META²V2V framework has been archived and is available at: DOI: 10.5281/zenodo.15747956
Cited by 0Open access
Samynathan, Sarath Kumar · NORMA · 2022
Unstructured data such as free text available in Electronic Health Records used in medical organizations are complex and hard to handle manually. Machine learning can be used to convert free text into vectors of tokens with the help of natural language processing and predict the outcome based on such conversion. Our aim of this project was to predict the ICD codes based on the synonyms of the diseases and we have predicted with the help of various machine learning algorithms and neural networks. We have used Random Forest, Support Vector, Logistic regression, Naive Bayes, KNN and MLP classifier to predict the ICD codes based on synonyms. We have also used the multilanguage embedding LASER so that the work can be used in multiple languages. The algorithm with highest accuracy is a random forest classifier, achieving 98% accuracy. Our results show that a reliable way to search for medical synonyms is made possible with traditional machine learning techniques. We therefore think that any user of such an application can successfully predict ICD codes based on synonyms.
Cited by 0
Allen Leung, Lal George · 1999
Static Single Assignment (SSA) is an effective intermediate representation in optimizing compilers. However, traditional SSA form and optimizations are not applicable to programs represented as native machine instructions because the use of dedicated registers imposed by calling conventions, the runtime system, and target architecture must be made explicit. We present a simple scheme for converting between programs in machine code and in SSA, such that references to dedicated physical registers in machine code are preserved. Our scheme ignores all output- and anti-dependences imposed by physical registers while a program is in SSA form, but inserts compensation code during machine code reconstruction if any naming requirements have been violated. By resolving all mismatches between the two representations in separate phases, we are able to utilize existing SSA algorithms unaltered to perform machine code optimizations.
Cited by 32Open access
Yang Yinan, Yujing Xie, Jun Ma et al. · ScienceDB · 2026
The code for assessing flood susceptibility using four machine learning algorithms (RF, XGBoost, CNN, LSTM).
Cited by 0Open access
Chalakorn Chitsaart, Suchada Rianmora, Mann Rattana-Areeyagon et al. · Zenodo (CERN European Organization for Nuclear Research) · 2013
G-code is the main factor in computer numerical control (CNC) machine for controlling the tool-paths and generating the profile of the object's features. For obtaining high surface accuracy of the surface finish, non-stop operation is required for CNC machine. Recently, to design a new product, the strategy that concerns about a change that has low impact on business and does not consume lot of resources has been introduced. Cost and time for designing minor changes can be reduced since the traditional geometric details of the existing models are applied. In order to support this strategy as the alternative channel for machining operation, this research proposes the automatic generating codes for CNC milling operation. Using this technique can assist the manufacturer to easily change the size and the geometric shape of the product during the operation where the time spent for setting up or processing the machine are reduced. The algorithm implemented on MATLAB platform is developed by analyzing and evaluating the geometric information of the part. Codes are created rapidly to control the operations of the machine. Comparing to the codes obtained from CAM, this developed algorithm can shortly generate and simulate the cutting profile of the part.
Cited by 0Open access
K. Charan Kumar, D. Srikanth, P. Vishnu Vardhan et al. · 2023
Vending machines are now widely used and recognized worldwide. Compared to traditional purchasing, vending machines are more convenient and accessible. Coinoperated vending machines are becoming obsolete as digital trade grows quickly. With the rise of smartphones & IoTs, QR codes are becoming more and more common these days. As a result, QR codes are being accepted for payments everywhere. To create a non-cash payment method utilizing a contactless mobile payment system, this vending machine leverages QR codes as a way for authorizing payments. The Finite State Machine is utilized to carry out this task. Behavioral modelling is used to create the Verilog code for the FSM-based machine, and the XILINX Vivado Design Suite tool is used to simulate the test bench.
Cited by 8
Chi Wu · Zenodo (CERN European Organization for Nuclear Research) · 2021
This instruction illustrates a machine learning-based multi-scale model to predict bone formation in tissue scaffolds. This code uses neural networks to predict bone formation in synthetic scaffolds. We are sorry that the code is a little bit messy as we are not good at coding. The code can be used to predict bone remodelling results in synthetic scaffolds in a multi-level way. Therefore, it enables to inversely identification of the bone remodelling related parameters from clinical data. In order to run the machine learning-based multiscale bone remodelling program. The following platforms are what you need: Abaqus v2016/v614 Matlab R2020b An Abaqus plugin tool which can be downloaded from https://github.com/mhogg/pyvxray.git Jupyter notebook with Python 3. <strong>Please see the related documents in version 1.1 (https://zenodo.org/record/5017032#.YNVVF-gzaUk)</strong>.
Cited by 0Open access
Chakravarthy, Ankur · Zenodo (CERN European Organization for Nuclear Research) · 2018
The R Markdown MLMarkdown_Final_withImages.Rmd contains all the machine learning code run for our cfMeDIP-Seq paper. The knit HTML MLMarkdown_Final_withImages.html contains the figures themselves as well.
Cited by 0Open access
Joseph R. Edelman · ScholarsArchive (Brigham Young University) · 2008
This Thesis is brought to you for free and open access by BYU ScholarsArchive. It has been accepted for inclusion in All Theses and Dissertations by an
Cited by 3Open access
Terrén-Serrano, Guillermo, Bashir, Abnan, Estrada, Trilce et al. · Zenodo (CERN European Organization for Nuclear Research) · 2022
This release includes the software for the operation of the Girasol Machine (sky imager), and the codes for the signal and image processing, in addition to the dataset generation. Guillermo Terrén-Serrano, Adnan Bashir, Trilce Estrada, Manel Martínez-Ramón, Girasol, a sky imaging and global solar irradiance dataset, Data in Brief, Volume 35, 2021, 106914, ISSN 2352-3409, https://doi.org/10.1016/j.dib.2021.106914.
Cited by 0Open access
Venkatesh Srinivasan, Thomas Reps · ACM SIGPLAN Notices · 2016
Machine-code slicing is an important primitive for building binary analysis and rewriting tools, such as taint trackers, fault localizers, and partial evaluators. However, it is not easy to create a machine-code slicer that exhibits a high level of precision. Moreover, the problem of creating such a tool is compounded by the fact that a small amount of local imprecision can be amplified via cascade effects. Most instructions in instruction sets such as Intel's IA-32 and ARM are multi-assignments: they have several inputs and several outputs (registers, flags, and memory locations). This aspect of the instruction set introduces a granularity issue during slicing: there are often instructions at which we would like the slice to include only a subset of the instruction's semantics, whereas the slice is forced to include the entire instruction. Consequently, the slice computed by state-of-the-art tools is very imprecise, often including essentially the entire program. This paper presents an algorithm to slice machine code more accurately. To counter the granularity issue, our algorithm performs slicing at the microcode level, instead of the instruction level, and obtains a more precise microcode slice. To reconstitute a machine-code program from a microcode slice, our algorithm uses machine-code synthesis. Our experiments on IA-32 binaries of FreeBSD utilities show that, in comparison to slices computed by a state-of-the-art tool, our algorithm reduces the size of backward slices by 33%, and forward slices by 70%.
Cited by 7
O. P. Sharma · International Journal on Advanced Computer Theory and Engineering · 2025
Automated code generation using machine learning techniques has emerged as a transformative approach to software development, enabling developers to generate high-quality code with minimal manual effort. This paper explores recent advancements in machine learning-driven code generation, focusing on deep learning models, transformer-based architectures, and large language models (LLMs) such as GPT, CodeBERT, and Codex. Key methodologies include natural language processing (NLP) for translating human-readable descriptions into executable code, reinforcement learning for improving code efficiency, and fine-tuning techniques to enhance model adaptability. We discuss various applications, including code completion, bug fixing, and optimization, while addressing challenges such as code correctness, security vulnerabilities, and domain-specific adaptations. Finally, we highlight future directions, emphasizing the need for explainability, improved dataset quality, and hybrid AI-human collaboration for robust and efficient automated code generation.
Cited by 0Open access
Samuel Allen Alexander · Figshare · 2018
We construct a machine that knows its own code, at the price of not knowing its own factivity.
Cited by 6Open access
Ermira Daka · International Journal of Applied Systemic Studies · 2023
Software maintenance is one of the most expensive phases of the software development life cycle. This cost increases more when maintenance is performed on poorly written code. There exist a set of code writing patterns that developers need to follow to write good-looking code. However, coding that conforms to 'rules' is not always possible. During software evolution, code goes through different changes, which are the main reasons for breaking the rules of beautiful code. In this paper, we propose a machine learning (ML)-based model which will measure the beauty of a written code. The model built on a set of ten code-based features is learned using logic regression algorithm and is able to predict how beautiful is given peace of code. Furthermore, the model is evaluated using an empirical study, which shows that it has a moderate agreement with developers about the beauty of the code.
Cited by 0
Roderic G. G. Cattell, Joseph M. Newcomer, Bruce W. Leverett · ACM SIGPLAN Notices · 1979
This paper presents some code generation issues in the context of the PQCC Production-Quality Compiler-Compiler project [8]. The approach taken is unusual in several ways. The machine-dependent information for selection of code sequences, register assignments, etc., has been separated throughout, in tabular form, from the machine-independent algorithms. This not only greatly simplifies the development of code generators for new machines or languages, but paves the way for automatic generation of these tables from formal machine descriptions such as ISP [1]. A parse-tree-like internal program representation is used, facilitating the use of context and data dependency information about expressions. The code generation process has been broken into several phases. This leads to simplification and better understanding of the code generation process, and also allows important improvements in the quality of generated code. The algorithms for preliminary determination of addressing modes, allocation of registers and other locations, and the code selection case analysis are discussed. The algorithms described in the paper are being implemented and used in the PQCC compiler.
Cited by 10Open access
Parosh Aziz Abdulla · 2013
Cited by 0
Isteaq Kabir Sifat (20469226), Md. Kaderi Kibria (14662982) · Figshare · 2024
Cited by 0Open access
Alexander Froemmgen, Jacob Austin, Peter Choy et al. · 2024
Code reviews are a critical part of the software development process, taking a significant amount of the code authors' and the code reviewers' time. As part of this process, the reviewer inspects the proposed code and asks the author for code changes through comments written in natural language. At Google, we see millions of reviewer comments per year, and authors require an average of ~60 minutes active shepherding time between sending changes for review and finally submitting the change. In our measurements, the required active work time that the code author must devote to address reviewer comments grows almost linearly with the number of comments. However, with machine learning (ML), we have an opportunity to automate and streamline the code-review process, e.g., by proposing code changes based on a comment's text.
Cited by 15Open access