Manuscript Topics

Pattern Recognition has shown its power in data mining and computer vision fields in recent years. Most pattern recognition systems are driven by data including image, video, audio, text, graph, structured data and so on. Development of data science has powered the demand to explore advanced methods under more complex data environments, in order to obtain more reliable, scalable, and insightful outcomes in challenging pattern recognition tasks. The complexity of data lies in the common multimodal, cross-domain, imbalanced, federated, graph, and causality data, and also data with concept drift, coupling effect, which bring great challenges including but not limited to data representation, model interpretability, computational efficiency, and optimization, to the existing pattern recognition methods. This special issue aims to present advanced and novel solutions to the above-mentioned challenges, which covers a broad range of research topics, including:

• classification,  
• anomaly detection,  
• representation learning,  
• streaming data analysis,  
• federated learning,  
• domain adaptation,  
• imbalanced data learning, and  
• optimization algorithm in pattern recognition tasks.

Contributions on theories, methods, models, frameworks, and new pattern recognition applications, in addition to new benchmark datasets, are welcomed.

Instructions for authors
https://www.aimspress.com/mbe/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/