Ramanujan-Inspired Hybrid Classical–Quantum Classification of Gravitational-Wave Glitches Using the Gravity Spy Dataset

This paper presented a Ramanujan-inspired hybrid classical–quantum framework for glitch classification using the Gravity Spy dataset. The final implementation followed a complete project structure that includes data loading, review of literature, methodology, system architecture, model setup, algorithm design, environment setup, result analysis, confusion-matrix interpretation, prediction logic, and comparative baseline analysis. The results show that the classical branch performs very strongly on the curated multi-class subset, with XGBoost achieving the highest accuracy, while the quantum branch demonstrates a feasible hybrid approach for binary glitch classification. The inclusion of system diagrams, workflow diagrams, glitch sample images, feature vector plots, PCA analysis, circuit diagrams, comparison tables, and confusion matrices makes the framework suitable for a full project report and IEEE-style paper submission. Future work may extend the bi- nary quantum setup to multiclass quantum classification, larger glitch subsets, and more advanced explainability strategies.

[1]     S. Tripathi, H. Upadhyay, and J. Soni, “A quantum machine learning- based predictive analysis of CERN collision events,” Scientific Reports, vol. 16, p. 682, 2026. [2]     G. S. Franco, F. Mahlow, P. M. Prado, G. E. L. Pexe, L. A. M. Rattighieri, and F. F. Fanchini, “Quantum phases classification using quantum machine learning with SHAP-driven feature selection,” Quan- tum Information Processing, vol. 25, p. 106, 2026. [3]     E. Adermann, H. Suzuki, and M. Usman, “Variational quantum machine learning with quantum error detection,” Quantum Machine Intelligence, vol. 8, p. 1, 2026. [4]     N. Dowling, M. T. West, A. Southwell et al., “Adversarial robustness guarantees for quantum classifiers,” npj Quantum Information, vol. 12, p. 16, 2026. [5]     A. Majumdar, “Quantum-stable robust principal component analysis: theory and evidence from NISQ regimes,” Quantum Machine Intelli- gence, vol. 8, p. 6, 2026. [6]     S. Jabeen, D. Kurdydyk, A. Palnitkar et al., “Quantum machine learning for state tomography using classical data,” Quantum Machine Intelli- gence, vol. 8, p. 40, 2026. [7]     F. Cirillo, C. Esposito, and J. T. Seo, “Benchmarking quantum machine learning methods for intrusion detection on noisy quantum computers,” Quantum Machine Intelligence, vol. 8, p. 27, 2026. [8]     M. Alharbi, “Modified transfer learning based variational quantum circuit for MNIST image classification,” Connection Science, vol. 38, no. 1, 2026. [9]     A. Engelsberger, M. Pšenicˇková, and T. Villmann, “Prototype- based classifiers and vector quantization on a quantum computer— implementing integer arithmetic oracles for nearest prototype search,” Entropy, vol. 28, no. 2, p. 229, 2026. [10]    G. Sergioli, C. Cuccu, C. S. Rieger, A. C. G. Arango, B. K. Behera, R. Era, and R. Giuntini, “A quantum-inspired classification for random mixed states,” Scientific Reports, vol. 16, p. 10668, 2026.