Authors : Bashir A. Sanusi; Emmanuel K. Ogunshile; Mehmet Aydin

Volume/Issue : Volume 11 - 2026, Issue 9 - September

Google Scholar : https://tinyurl.com/4yawz75m

DOI : https://doi.org/10.38124/ijisrt/26sep417

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The increasing complexity of modern software systems demands more intelligent and reliable compiler designs capable of detecting code anomalies efficiently. Traditional compilers, while effective in syntax and semantic analysis, lack adaptive capabilities for identifying non-trivial errors. This paper presents a performance-aware hybrid compiler that integrates the Communicating Stream X-Machine (CSXM) formal framework with Machine Learning (ML) techniques for intelligent code analysis. The approach combines formal verification with predictive models, including Random Forest, Convolutional Neural Networks (CNN), and CNN-LSTM architectures. Experimental evaluation was conducted using both real-world (DeepFix) and synthetically generated datasets, with over 150 training and testing iterations. Performance was assessed using accuracy, precision, recall, and F1-score. In addition, this study provides a detailed analysis of compilation latency and ML inference overhead, highlighting the trade-off between detection accuracy and execution efficiency. Results show that ML integration significantly improves anomaly detection but introduces measurable latency. The paper also discusses practical challenges, including dataset labelling effort and model generalisability. These findings demonstrate that a performance-aware hybrid CSXM–ML compiler offers a promising approach for developing intelligent, adaptive compilation systems that balance correctness, efficiency, and scalability.

Keywords : Compiler, Communicating Stream X-Machine, Machine Learning, Random Forest, Convolutional Neural Network, Long Short-Term Memory, Anomaly Detection, Software Development.

References :

1. Akhtar, N. and Missen, M.M (2014). Contribution to the Formal Specification and Verification of a Multi-Agent Robotic System. European Journal of Scientific Research. ISSN 1450-216X / 1450-202X Vol.117 No.1. Page 35-55.
2. Barchi, F., Parisi, E., Urgese, G., Ficarra, E. and Acquaviva, A. (2020). Exploration of Convolutional Neural Network Models for Source Code Classification. Engineering Applications of Artificial Intelligence. https://doi.org/10.1016/j.engappai.2020.104075
3. Bhowmick, K. and Narvekar, M. (2019). A Comprehensive Study and Analysis of Semi-Supervised Learning Techniques. International Journal of Engineering Research and Technology (IJERT). Vol. 8. Issue 11. Page 810-816.
4. Chaflekar, S. H., Lokhande, A., Gomase, P. and Shinganjude, R. (2017). Compiler Architecture and Design Issues. International Journal of Computer Science Trends and Technology (IJCST). Volume 5. Issue 3.
5. Chen, J., Hu, W., Hao, D., Xiong, Y., Zhang, H. Zhang, L. and Xie, B. (2016). An Empirical Comparison of Compiler Testing Techniques. In Proceedings of the 38th International Conference on Software Engineering. Page 180-190.
6. Chen, Z., Bihuan, C., Linlin, C., Xin, P., and Wenyun, Z. (2019a). A Large-Scale Empirical Stud of Compiler Errors in Continuous Integration. In Proceedings of the 27th ACM Joint European Software Engineering Confereence and Symposium on the Foundations of Software Engineering (ESEC/FSE ’19). Tallinn, Estonia. ACM, New York, NY, USA, 12 pages. https://doi.org/10.1145/3338906.3338917
7. Chen, R., Wang, X., Zhang, W., Zhu, X., Li, A., and Yang, C. (2019b). A hybrid CNN-LSTM model for typhoon formation forecasting, GeoInformatica, 23, 375–396, 2019.
8. Dehaerne, E., Dey, B., Gendt, S. D. and Meert, W. (2022). Code Generation Using Machine Learning: A Systematic Review. IEEE Access. DOI: 10.1109/ACCESS.2022.3196347.
9. Fatemehalsadat, M., Karem, C., Rachid, L., Saeid, H., Yves, G., and Simon, T. (2020). Convolutional neural network and long short-term memory models for ice-jam predictions. The Cryosphere, 16, 1447–1468, 2022 https://doi.org/10.5194/tc-16-1447-2022.
10. Goerigk, W., Dold, A., Gaul, T., Goos, G., Heberle, A. Henke, F. W., Hoffmann, U., Langmaack, H., Pfeifer, H., Ruess, H. and Zimmermann, W. (2015). Compiler Correctness and Implementation Verification: The Verifix Approach. ResearchGate. https://www.researchgate.net/publication/2274826.
11. Gupta, R., Pal, S., Kanade, A. and Shevadem S. (2017). DeepFix: Fixing Common C language Errors by Deep Learning. AAAI 2017.
12. Hanifeng, W., Hengyuan, L. Zheng, L., Yong, L., Fuxiang, S., and Xiang, C. (2022). A Token-Based Compilation Error Categorization and Its Applications. J Softw Evol Proc. 2022; e2512. wileyonlinelibrary.com/journal/smr. © 2022 John Wiley & Sons Ltd. https://doi.org/10.100
13. Hela, B. K. (2024). Intelligent Compilers: Machine Learning-Powered Compiler Autotuning. Medium. https://itnext.io/intelligent-compilers-machine-learning-powered-compiler-autotuning-929ae8fe407f.
14. Jayatilaka, T., Ueno, H., Georgakoudis, G., Park, E. and Doerfert, J. (2021). Towards Compile-Time-Reducing Compiler Optimization Selection via Machine learning. ICPP Workshops ’21, Lemont, IL, USA. ACM ISBN 978-1-4503-XXXX-X/18/06. https://doi.org/10.1145/1122445.1122456
15. Junjie, C., Wenxiang, H., Dan, H., Yingfei, X., Hongyu, Z., Lu, Z., and Bind, X. (2016). An Empirical Comparison of Compiler Testing Technique. ICSE ’16, Austin, TX, USA.  http://dx.doi.org/10.1145/2884781.2884878
16. Li, X., Zhang, Y., Zhang, J., Chen, S., Marsic, I., Farneth, R. A., and Burd, R. S. (2017). Concurrent activity recognition with multimodal CNN-LSTM structure, arXiv:1702.01638.
17. Luan, Y. and Lin, S. (2019). Research on text classification based on CNN and LSTM, in: International Conference on Artificial Intelligence and Computer Applications, Dalian, China, 352–355, https://doi.org/10.1109/ICAICA.2019.8873454.
18. Lu, N., Wu, Y., Feng, L., and Song, J. (2018). Deep learning for fall detection: Three-dimensional CNN combined with LSTM on video kinematic data, IEEE J. Biomed. Health, 23, 314–323.
19. Maas, M, Andersen, D. G., Isard, M. Javanmard, M. M., Mckinley, K. S. and Colin, R. (2020). Combining Machine Learning and Lifetime-Based Resource Management for Memory Allocation and Beyond. In Proceedings of the 25th International Conference on Architectural Support for Programming Languages and Operating Systems, 2020. DOI:10.1145/3611018.
20. Mesbah, A., Rice, A., Aftandilian, E., Johnston, E., and Glorioso, N. (2019). DeepDelta: Learning to Repair Compilation Errors. In Proceedings of the 27th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2019). ACM, NewYork, NY, USA, 12pages. https://doi.org/10.1145/nnnnnnn.
21. Monsifrot, A., Bodin, F. and Quiniou, R. (2002). A Machine Learning Approach to Automatic Production of Compiler Heuristics. In Proceedings of the International Conference on Artificial Intelligence. Methodol. Syst. Appl. Page 41- 50.
22. Mutegeki, R. and Han, D. S. (2020). A CNN-LSTM approach to human activity recognition, in: International Conference on Artificial Intelligence in Information and Communication, Fukuoka, Japan, 362–366, https://doi.org/10.1109/ICAIIC48513.2020.9065078.
23. Ogunshile E. (2011). A Machine with Class: A Framework for Object Generation, Intergration and Language Authentication (FROGILA). Ph.D. Thesis. The University of Sheffield. United Kingdom.
24. Oh, S. L., Ng, E. Y., San Tan, R., and Acharya, U. R. (2018). Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats, Comput. Biol. Med., 102, 278–287.
25. Ombabi, A. H., Ouarda, W., and Alimi, A. M. (2020). Deep learning CNN–LSTM framework for Arabic sentiment analysis using textual information shared in social networks, Social Network Analysis and Mining, 10, 1–13, https://doi.org/https://doi.org/10.1007/s13278-020-00668-1.
26. Ordóñez, F. J. and Roggen, D. (2016). Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition, Sensors, 16, 115–140 https://doi.org/10.3390/s16010115.
27. Patterson, D. and Ahmed, A. (2019). The Next 700 Compiler Correctness Theorems (Function Pearl). Proc. ACM Program. Lang. 3, ICFP, Article 85. Page 1-29. https://doi.org/10.1145/3341689
28. Pizzolotto, D. and Inoue, K. (2021). Identifying Compiler and Optimization Level in Binary Code from Multiple Architectures. IEEE Access Digital Object Identifier 10.1109/ACCESS.2021.3132950. Volume 9. Page 1- 15.
29. Raphael, M., David, L., Wolfgang, K., Lukas Stadler, and Hanspeter, M. (2022). Machine-Learning-Based Self-Optimizing Compiler Heuristics. In Proceedings of the 19th International Conference on Managed Programming Languages and Runtimes (MPLR ’22). Brussels, Belgium. ACM, New York, NY, USA, 14 pages. https: //doi.org/10.1145/3546918.3546921
30. Sanusi, B. A., Olabiyisi, S. O., Olowoye, A. O. and Olatunji, B. L. (2019). Software Defect Prediction System using Machine Learning based Algorithms. Journal of Advances in Computational Intelligence Theory, 1(3), 1–9. http://doi.org/10.5281/zenodo.35908 41
31. Sanusi, B. A., Ogunshile, E., Aydin, M., and Olabiyisi, S. O. (2024). Assuring Correctness, Testing, and Verification of X-Compiler by Integrating Communicating Stream X-Machine. In 2024 6th International Conference on Software Engineering and Development (ICSED 2024), May 29–31, 2024, Hong Kong, Hong Kong. ACM, New York, NY, USA, 9 pages.
32. Sanusi B. A., Ogunshile E. K. A., Aydin, M. E., Olabiyisi, S. O. and Oyediran M. O. (2022). Development of Communicating Stream X-Machine Tool for Modeling and Generating Test Cases for Automated Teller Machine. 9th International Conference on Computer Science and Information Technology (CSIT 2022), DOI: 10.5121/csit.2022.121407 pp 77-90.
33. She, X. and Zhang, D. (2018). Text classification based on hybrid CNN-LSTM hybrid model, in: 11th International Symposium on Computational Intelligence and Design, 185–189, https://doi.org/10.1109/ISCID.2018.10144.
34. Shi, R., Hu, J., and Lin, B. (2023). Mining on Students’ Execution Logs and Repairing Compilation Errors Based on Deep Learning. Appl. Sci. 2023, 13, 9933. https://doi.org/10.3390/app13179933
35. Shreyas, M., Siddarth, S., and Karmel, A. (2021). Memory Utilization and Machine Learning Techniques for Compiler Optimization. ITM Web of Conferences 37, 01021 (2021) https://doi.org/10.1051/itmconf/20213701021.
36. Simon, A., Deo, M. S., Venkatesan, S., and Babu, R. (2015). An Overview of Machine Learning and It’s Applications. International Journal of Electrical Sciences & Engineering (IJESE). Volume 1. Issue 1. Page 22-24.
37. Sosa, P. M.(2017). Twitter sentiment analysis using combined LSTM CNNmodels, Eprint Arxiv, 1–9.
38. Sun, C., Le, V., Su, Z.(2016). Finding and analyzing compiler warning defects. In: Proceedings of the 38th International Conference on Software Engineering, ICSE 2016 .Austin, TX, USA, May 14-22, 2016. pp. 203–213. ACM (2016). https://doi.org/10.1145/2884781.2884879
39. Tang, Y., Jiang, H., Zhou, Z., Li, X., Ren, Z. and Kong, W. (2020). Detecting Compiler Warning Defects Via Diversity-Guided Program Mutation.  IEEE Transactions on Software Engineering. DOI: 10.1109/TSE.2021.3119186
40. Umer, M., Imtiaz, Z., Ullah, S., Mehmood, A., Choi, G. S., and On, B. W. (2020). Fake news stance detection using deep learning architecture (cnn-LSTM), IEEE Access, 8, 156695–156706.
41. VenkataKeerthy, S., Jain, S., Kalvakuntla, U., Gorantla, P. S., Chitale, R. S., Brevdo, E., Cohen, A., Trofin, M., and Upadrasta, R. (2024). The Next 700 ML-Enabled Compiler Optimizations. In Proceedings of the 33rd ACMSIGPLAN International Conference on Compiler Construction (CC ’24), March 2–3, 2024, Edinburgh, United Kingdom. ACM, New York, NY, USA, 12 pages. h ps://doi.org/10.1145/3640537.3641580
42. Wang, J., Yu, L. C., Lai, K. R., and Zhang, X.(2016b). Dimensional sentiment analysis using a regional CNN-LSTM model, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 225–230, Berlin, Germany, https://doi.org/10.18653/v1/P16-2037.
43. Wang, Z. and O’Boyle, M. (2018). Machine Learning in Compiler Optimization. Proceedings of the IEEE. Vol. 106. No. 11. Page 1879 – 1901. https://doi.org/10.1109/JPROC.2018.2817118
44. Wang, J., Yu, L. C., Lai, K. R., and Zhang, X. (2019). Tree-structured regional CNN-LSTM model for dimensional sentiment analysis, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 581–591.
45. Wu, Z., Wang, X., Jiang, Y. G., Ye, H., and Xue, X. (2015). Modeling spatial-temporal clues in a hybrid deep learning framework for video classification, in: 23rd ACM International Conference on Multimedia, Brisbane Australia, 461–470, https://doi.org/10.1145/2733373.2806222.
46. Yamashita, R., Nishio, M., Do, R. K. and Togashi, K. (2018). Convolutional Neural Networks: An Overview and Application in radiology. Insights into Imaging (2018) 9:611–629 https://doi.org/10.1007/s13244-018-0639-9
47. Yang, X., Chen, Y., Eide, E. and Regehr, J. (2011). Finding and Understanding Bugs in C Compilers. In Proceedings of the 32nd ACM SIGPLAN Conference on Programming Language Design and Implementation. Page 283–294.
48. Yang, S., Shi, Z., and Zhang, G. (2023). Understand Code Style: Efficient CNN-based Compiler Optimization Recognition System. ArXiv:2302.04666v1 [cs.PL].
49. Yacine, H., Riyadh, B., and Yacine, C. (2023). A Hybrid Machine Learning Model for Code Optimization. International Journal of Parallel Programming. 51:309–331https://doi.org/10.1007/s10766-023-00758-5.
50. Yixuan, T., He, J., Zhide, Z., Xiaochen, L., and Zhilei, R. (2021). Detecting Compiler Warning Defects Via Diversity-Guided Program Mutation. IEEE Transactions on Software Engineering. 0098-5589. Page 1-12.
51. Zheng, W. and Michael, O. (2018). Machine Learning in Compiler Optimization. arXiv:1805.0344lv1.