ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 12. Vol. 31. 2025

DOI: 10.17587/it.31.659-669

V. V. Kureichik, Dr. of Eng. Sc., Professor, V. I. Danilchenko, Ph.D. Tech. Sc., Associate Professor,
Southern Federal University, Taganrog, Russian Federation

Anomaly Detection and Prediction in VLSI Design Workflows

Received on 16.06.2025
Accepted on 27.06.2025

This study addresses the problem of intelligent anomaly prediction during the early stages of very-large-scale integration (VLSI) design, under the constraints of increasingly complex topologies and modern technological standards. The problem formulation includes the formalization of criteria for anomaly detection, such as congestion zones, topological conflicts, and routing violations. To enhance classification accuracy and adaptability to diverse design data structures, a hybrid architecture is proposed that combines metaheuristic methods with machine learning algorithms. À computational experiment was conducted using both synthetic and publicly available datasets, demonstrating the effectiveness of the stacking model and graph neural networks in achieving high prediction quality within acceptable training times. The study also explores the impact of cross-validation and class balancing on resistance to overfitting. The obtained results confirm the practical applicability of the proposed approach in modern computer-aided design (CAD) systems. This article will be of interest to specialists in design automation and intelligent analysis of VLSI systems, as well as researchers working on hybrid methods in engineering applications.
Keywords: hybrid architecture, metaheuristic methods, machine learning, classification, anomaly prediction, VLSI, topological conflicts, design optimization, cross-validation

cknowledgments. The research was funded by the Russian Science Foundation project No. 24-71-00035, https://rscf.ru/project/24-71-00035/ implemented by the Southern Federal University.

P. 659-669

Full text on eLIBRARY

References

1. Sherwani N. A. Algorithms for VLSI Physical Design Automation, USA, Kluwer Academic Publisher, 2013, 567 p.
2. Taur Y., Ning T. H. Fundamentals of Modern VLSI Devices, Cambridge, Cambridge University Press, 2022, 622 p.
3. Kazennov G. G. Fundamentals of Integrated Circuit and System Design. Moscow, Binom. Knowledge Laboratory, 2005, 295 p. (in Russian).
4. Kureichik V. V., Zaporozhets D. Yu. Modern problems of VLSI component placement, Izvestiya of South Federal University. Technical Sciences, 2011, no. 7 (120), pp. 68—73 (in Russian).
5. Kureichik V. V., Gladkov L. A., Kravchenko Yu. À ., Rodzin S. I. Intelligent Systems: Models and Methods of Metaheuristic Optimization, Cheboksary, Sreda Publishing House, 2024, 228 p. (in Russian).
6. Karpenko À . P. Modern Search Optimization Algorithms: Nature-Inspired Algorithms, Moscow, Bauman MSTU Publish­ing, 2021, 448 p. (in Russian).
7. Sapozhnikov V. M., Sergeev À . N. Hybrid neural network architectures in technical diagnostics, Izvestiya of South Federal University. Technical Sciences, 2020, no. 4, pp. 105—113 (in Russian).
8. Zhang X., Liu C., Liu Z. et al. À dual-stream neural network architecture for detecting layout hotspots in VLSI design, IEEE Trans. on Computer-Aided Design of Integrated Circuits and Systems, 2021,vol. 40, no. 9, pp. 1764—1777.
9. Ahmed M., Hasan M. M., Mahmud S. H. fSEAD: À scalable FPGA-based ensemble framework for real-time anomaly detection in hardware systems, IEEE Trans. on Computers, 2022, vol. 71, no. 12, pp. 3034—3048.
10. Chen Z., Liu Y., Wang S. et al. CAE-T: Convolutional autoencoding transformer for multivariate time series anomaly detection, Proc. 30th ACM Int. Conf. on Information and Knowledge Management (CIKM), 2021, pp. 1623—1632.
11. Xu D., Ruan C., Korpeoglu E., Kumar S., Achan K. Inductive representation learning on temporal graphs, Proc. Int. Conf. on Learning Representations (ICLR), 2020, pp. 1—18.
12. Li H., Wen W., Li P. À survey on hybrid neural networks for graph and grid data in EDA, ACM Trans. on Design Automation of Electronic Systems (TODAES), 2022, vol. 27, no. 6, pp. 1—25.
13. Kar B., Gopalakrishnan P. K., Bose S. K., Roy M., Basu A. ADIC: Anomaly detection integrated circuit in 65nm CMOS utilizing approximate computing, IEEE Trans. on VLSI Systems, 2020,vol. 28, no. 11, pp. 2481—2490.
14. Danilchenko V. I., Danilchenko Y. V., Kureichik V. M. Application of genetic algorithms in solving the problem of placing elements on a crystal considering the maximum number of linear segments, Proc. 5th Int. Scientific Conf. "Intelligent Information Technologies for Industry", 2021, pp. 10—14.
15. Rodzin S. I., Skobtsov Yu. À ., El-Khatib S. A. Bioheuristics: Theory, Algorithms and Applications, Cheboksary, Sreda Publishing House, 2019, 224 p. (in Russian).
16. Danilchenko V. I., Danilchenko E. V., Kureichik V. M. Representation of matrix architecture as a working field in the problem of initial placement of VLSI components, Problems of Developing Advanced Micro- and Nanoelectronic Systems (MES), 2022, no. 2, pp. 20—25 (in Russian).
17. Yamaguchi H., Otsuka Y., Inoue T. Early detection of placement and routing errors using layout-aware risk metrics in VLSI design, IEEE Trans. on Computer-Aided Design of Integrated Circuits and Systems, 2022, vol. 41, no. 3, pp. 745—758.
18. Zhang Y., Jin R. À gradient boosting-based framework for design rule violation detection in VLSI physical design, IEEE Trans. on Computer-Aided Design of Integrated Circuits and Systems, 2020, vol. 39, no. 11, pp. 3243—3255.
19. 1Sanchez Lopera D., Servadei L., Kiprit G. N., Wille R., Eck er W. À comprehensive survey on electronic design automation and graph neural networks: Theory and applications, ACM Trans. on Design Automation of Electronic Systems (TODAES), 2021, vol. 26, no. 6, pp. 1—35.
20. Danilchenko V. I., Danilchenko Y. V., Kureichik V. M. The mechanism of encoding and decoding solutions when placing VLSI components with different orientations and sizes. Journal of Information Assurance & Security, 2023, vol. 18, no. 3, pp. 79—88.
21. Zhou Z. H. Ensemble Methods: Foundations and Algorithms, Boca Raton, CRC Press, 2012, 720 p.
22. Song J., Liu J. ISMOTE: À more accurate alternative for SMOTE, Neural Processing Letters, 2024, vol. 56, pp. 240—256.
23. Stempkovsky A. L., Telpukhov D. V., Zhukova T. D., Gurov S. I., Solovyev R. A. Methods of synthesizing fault-tolerant CMOS combinational circuits providing automatic error correction, Izvestiya of South Federal University. Technical Sciences, 2017, no. 7 (192), pp. 197—210 (in Russian).
24. De Souza L. A. M., Da Silva J. E. Í ., Chaves L. J., Bernardino H. S. À benchmark suite for designing combinational logic circuits via metaheuristics, Applied Soft Computing, 2020, vol. 91, pp. 1—32.
25. Govia L. C. G., Jurcevic P., Wood C. J. et al. À randomized benchmarking suite for mid-circuit measurements, New Journal of Physics, 2023, vol. 25, no. 12, pp. 1—24.

To the contents