Publications
Below are five selected representative publications. For a full list, please visit my Google Scholar Page.
1. Saliency Detection for Underwater Moving Object with Sonar Based on Motion Estimation and Multi-Trajectory Analysis
Zhu, J., Cai, W., Zhang, M., Lin, Y., and Liu, M.
Pattern Recognition, 2025, 158, 111043.
Published in the top-tier journal Pattern Recognition (Impact Factor: 7.5, Q1), this paper proposes a saliency detection framework for tracking underwater moving objects. The approach integrates motion estimation, trajectory analysis, and a local-to-global saliency mapping model, and is validated using a custom sonar data acquisition system. Extensive experiments on eight sonar videos demonstrate superior performance over 15 state-of-the-art methods.
2. Unraveling the Implementation Processes of PEDs: Lessons Learned from Multiple Urban Contexts
Gohari, S., Silvia, S.C., Ashrafian, T., Konstantinou, T., Giancola, E., Prebreza, B., Aelenei, L., Murauskaite, L., and Liu, M.
Sustainable Cities and Society, 2024, Article 105402.
Published in the high-impact journal Sustainable Cities and Society (Impact Factor: 10.5, Q1), this study investigates the implementation of Positive Energy Districts (PEDs) through qualitative interviews with stakeholders across several European cities. As lead author, I contributed to shaping urban sustainability discussions, with policy-relevant findings for a zero-carbon future.
3. Privacy-Aware Energy Consumption Modeling of Connected Battery Electric Vehicles using Federated Learning
Yan, S., Fang, H., Li, J., Ward, T., O’Connor, N., and Liu, M.
IEEE Transactions on Transportation Electrification, 2023.
Published in IEEE Transactions on Transportation Electrification (Impact Factor: 7.2, Q1), this paper introduces a novel federated learning framework for privacy-preserving modeling of energy consumption in connected electric vehicles. As lead author, I oversaw the project and manuscript, ensuring research quality and integrity. The work has drawn interest from major automotive stakeholders in Ireland, including Nissan, Toyota, and Renault.
4. MPC-CSAS: Multi-Party Computation for Real-Time Privacy-Preserving Speed Advisory Systems
Liu, M., Cheng, L., Gu, Y., Wang, Y., Liu, Q., and O’Connor, N.E.
IEEE Transactions on Intelligent Transportation Systems, 2021, 23(6), pp. 5887–5893.
This paper, published in IEEE Transactions on Intelligent Transportation Systems (Q1, Impact Factor: 7.9), presents a real-time privacy-preserving framework using multi-party computation for speed advisory systems. It demonstrates low latency and high efficiency, making it suitable for large-scale deployment without additional ICT infrastructure. The work was nominated for recognition within the ITS Society.
5. A Distributed Markovian Parking Assist System
Liu, M., Naoum-Sawaya, J., Gu, Y., Lecue, F., and Shorten, R.
IEEE Transactions on Intelligent Transportation Systems, 2018, 20(6), pp. 2230–2240.
This paper, published in IEEE Transactions on Intelligent Transportation Systems (Q1, Impact Factor: 7.9), presents a distributed parking guidance system that leverages ant colony optimization and Markovian signaling to direct drivers to on-street parking with minimal infrastructure. By recommending routes based on parking likelihood and travel cost, the system balances congestion and improves search efficiency. Validated using SUMO simulations and real data from Dublin, it achieves significant reductions in travel time and distance.