Quantum Machine Learning for Time Series Anomaly Detection

This project explores the potential of quantum machine learning (QML) algorithms for time series anomaly detection (TAD), a crucial task in areas such as healthcare, finance, and cloud systems. While classical approaches have achieved notable success, challenges remain in capturing complex temporal dependencies, modeling high-dimensional correlations, and ensuring timely detection of anomalies. By leveraging QML-based algorithms, the project aims to develop more accurate and efficient solutions for detecting unusual patterns in time series data from complex systems. The research will be jointly conducted by the Gran Sasso Science Institute in Italy and Toronto Metropolitan University in Canada, fostering collaboration in quantum computing and AI-driven anomaly detection. Both institutions will benefit from shared expertise, joint publications, and knowledge exchange, which will strengthen their international partnerships and contribute to Canada’s leadership in quantum innovation.

Faculty Supervisor:

Andriy Miranskyy

Student:

Partner:

Gran Sasso Science Institute

Discipline:

Computer science

Sector:

Education

University:

Toronto Metropolitan University

Program: