Hybrid quantum-classical machine learning for industrial multi-anomaly detection via single acoustic sensor
- 1Graduate School of Science and Technology, Keio University
- 2Department of Smart Technologies, Digital Innovation Div., Toppan Holdings
Abstract
We developed a novel workflow that leverages Quantum Kernel feature space expressiveness combined with classical dimensionality reduction techniques. This workflow enables detection and visual identification of multiple simultaneous anomalies using acoustic data from a single non-contact sensor. Our newly developed method provides an intuitive interface for operators to identify specific anomalies. By combining conventional Mel-frequency cepstral coefficients (MFCC) with principal component analysis (PCA), the newly constructed Quantum Kernel achieves near-perfect classification (F1 = 1.0 under specific conditions: j ≥ 9 features, file-level data splits) of complex multi-source anomalies, significantly outperforming the classical RBF kernel (F1 ≈ 0.75–0.76) and 1D-CNN autoencoder baseline (F1 ≈ 0.60–0.85). The Quantum Kernel’s superior representational power enables accurate anomaly detection with minimal training data. Our results demonstrate simulation-based evidence of potential quantum advantage under ideal conditions, where the performance of our method dramatically exceeds that of classical approaches as the number of features increases, pending validation on noisy intermediate-scale quantum (NISQ) hardware. This hybrid quantum-classical machine learning approach demonstrates significant potential for industrial applications, particularly for complex time-series data in data-scarce regimes where classical methods exhibit limited performance.
Related
- Quantum-classical hybrid learning framework for Parkinson’s disease prediction using acoustic and clinical features
- Asymmetric class-conditional routing in a federated quantum mixture-of-experts improves imbalanced intrusion detection in edge industrial IoT networks
- Cross-corpus consensus feature selection for language-invariant Parkinson’s disease detection: a dual-stream acoustic and spectrogram-attention framework
- Optimizing energy consumption in industrial wireless sensor networks using a hybrid FCM and GWO machine learning approach
- Predicting MCI-to-Alzheimer’s Conversion: A Systematic Benchmark of Classical, Machine Learning, and Deep Survival Models
BibTeX
@article{tomono2026hybrid,
title = {{Hybrid quantum-classical machine learning for industrial multi-anomaly detection via single acoustic sensor}},
author = {Takao Tomono and Kazuya Tsujimura},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-61786-y},
url = {https://doi.org/10.1038/s41598-026-61786-y},
note = {CC BY},
}
RIS
TY - JOUR
TI - Hybrid quantum-classical machine learning for industrial multi-anomaly detection via single acoustic sensor
AU - Takao Tomono
AU - Kazuya Tsujimura
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-61786-y
UR - https://doi.org/10.1038/s41598-026-61786-y
AB - We developed a novel workflow that leverages Quantum Kernel feature space expressiveness combined with classical dimensionality reduction techniques. This workflow enables detection and visual identification of multiple simultaneous anomalies using acoustic data from a single non-contact sensor. Our newly developed method provides an intuitive interface for operators to identify specific anomalies. By combining conventional Mel-frequency cepstral coefficients (MFCC) with principal component analysis (PCA), the newly constructed Quantum Kernel achieves near-perfect classification (F1 = 1.0 under specific conditions: j ≥ 9 features, file-level data splits) of complex multi-source anomalies, significantly outperforming the classical RBF kernel (F1 ≈ 0.75–0.76) and 1D-CNN autoencoder baseline (F1 ≈ 0.60–0.85). The Quantum Kernel’s superior representational power enables accurate anomaly detection with minimal training data. Our results demonstrate simulation-based evidence of potential quantum advantage under ideal conditions, where the performance of our method dramatically exceeds that of classical approaches as the number of features increases, pending validation on noisy intermediate-scale quantum (NISQ) hardware. This hybrid quantum-classical machine learning approach demonstrates significant potential for industrial applications, particularly for complex time-series data in data-scarce regimes where classical methods exhibit limited performance.
SN - 2045-2322
ER -