Open Access Open Access  Restricted Access Subscription Access

INTELLIGENT COMPILER : GIVES SUGGESTIONS AND IMPROVEMENTS

Kadhiravan EG, Karthiban R, Dharshini L, Dharshini S, Hanushree L

Abstract


This research focuses on developing smart techniques for automatically detecting and fixing errors in programs written in various programming languages. It uses machine learning (ML) and natural language processing (NLP) methods to analyze source code, find syntax or runtime errors, and provide precise correction suggestions. By studying different programming structures and common error patterns, the project aims to make code debugging faster, more efficient, and more reliable. The results of this study can support the creation of advanced compiler systems and interactive learning tools for programmers. Overall, this work combines intelligent automation with practical coding support to build more accurate, responsive, and user-friendly programming environments.


Full Text:

PDF

References


Sharma, R., & Patel, K. (2023). A multi-language code error detection framework for beginner programmers. International Journal of Computer Applications, 182(4), 45–50.

Zhang, Y., & Liu, H. (2022). Machine learningbased code error prediction and correction. Journal of Software Engineering Studies, 19(3), 112–120.*

Kumar, S., & Mehta, P. (2021). Intelligent syntax analyzer for programming languages using NLP techniques. International Research Journal of Computer Science, 15(2), 58– 67.*

Gupta, N., & Singh, R. (2024). Code error detection in multi-language compilers. Proceedings of the National Conference on Emerging Computing Trends, 34–40.*

Gordon, D., & Brown, T. (2023). Automated bug detection using hybrid static and dynamic analysis. IEEE Transactions on Software Systems, 31(7), 284–290.*

Li, Y., & Abhimanyu, K. (2022). Real-time feedback systems for programming education. International Journal of Educational Technology, 28(4), 93–99.*

Chen, A., & Lucas, P. (2024). Error classification and correction for C and Java programs. International Journal of Advanced Computing Research, 30(2), 67–74.*

Wilson, M., & Taylor, J. (2021). Automated code review and feedback using deep learning models. ACM Computing Surveys, 52(1), 1–9.*

Tan, J., & Ho, S. (2023). Hybrid frameworks for multilanguage syntax checking. Journal of Computational Systems, 19(4), 36–43.*

Pereira, L., & Das, K. (2024). Enhancing programming accuracy through intelligent debugging systems. Education and Information Technologies, 32(6), 177– 184.*


Refbacks

  • There are currently no refbacks.