Mining Data Streams and Graph Mining

1. Mining Data Streams Mining data streams involves processing potentially infinite sequences of data tuples on the fly using methods like sliding windows and synopsis structures to summarize recent items in real time Data Streams in Data Mining Simplified 101 - Hevo Data Data stream analysis: Foundations, major tasks and tools

1. Frequent Pattern Mining in Stream Data Frequent pattern mining over streams finds itemsets whose occurrence frequency exceeds a threshold within a moving window, often using approximate counting (e.g., Lossy Counting) to handle high-speed data Frequent Pattern Mining in Data Streams | SpringerLink Frequent pattern mining on stream data using Hadoop CanTree-GTree

1. Sequential Pattern Mining in Data Streams Sequential pattern mining discovers frequent subsequences (ordered patterns) in streaming transaction sequences by using sliding-window or bitmap-based algorithms to track temporal order under memory constraints An Introduction to Sequential Pattern Mining | The Data Blog Automatic Sequential Pattern Mining in Data Streams

1. Classification of Dynamic Data Streams & Class Imbalance Dynamic stream classification builds models incrementally and adapts to concept drift—changes in the data distribution—while addressing class imbalance by techniques like resampling or cost-sensitive learning Classification of the drifting data streams using heterogeneous … | PeerJ Classification Of Dynamic Data Streams | SkedBooks

1. Graph Mining & Social Network Analysis Graph mining extracts patterns such as frequent subgraphs, communities, and influential nodes from network-structured data; social network analysis applies these methods to uncover relationships and information flow in social graphs Using Graph Mining to Explore Social Networks - Medium Graph Theory and Algorithms for Social Network Analysis