Aim and Scope
Fusion: Practice and Applications (FPA) is an international, peer-reviewed journal dedicated to the theories, methods, systems, and real-world applications of information fusion.
The journal publishes original research articles and review papers that integrate information from multiple sources, sensors, modalities, features, models, or decision processes to improve estimation, recognition, prediction, decision-making, robustness, and system reliability.
Topics covered by the journal include:
• Data, feature, score, rank, decision, and multilevel fusion
• Multisensor and multimodal information fusion
• Statistical, Bayesian, fuzzy, neural, and evidence-based fusion
• Fusion system architectures, design, and optimization
• Pattern recognition, classification, estimation, and tracking
• Machine learning and deep learning for information fusion
• Uncertainty modelling, explainability, reliability, and robustness
• Information fusion in robotics, autonomous systems, remote sensing, healthcare, cybersecurity, the Internet of Things, transportation, finance, and industrial systems
• Real-time, distributed, privacy-preserving, and edge-based fusion systems
Every submission must present a clear and substantive information-fusion contribution. Papers that merely apply artificial intelligence, machine learning, optimization, or data analytics without integrating multiple information sources, modalities, representations, models, or decisions fall outside the journal’s scope.