IATVI 2012 - The International Special Session on Intelligent Analysis of Time Varying Information and Concept Drift Management

Intelligent Analysis of Time Varying Information and Concept Drift Management
[Session Chairs]: Jean-Charles Lamirel (lamirel-AT-loria.fr), Pascal Cuxac (pascal.cuxac-AT-inist.fr)
[Scope]: The development of dynamic information analysis methods, like incremental clustering, concept drift management and novelty detection techniques, is becoming a central concern in a bunch of applications whose main goal is to deal with information which is varying over time. These applications relate themselves to very various and highly strategic domains, including web mining and adaptive information retrieval, user behaviour analysis and recommendation systems, technological and scientific survey, anomaly or intrusion detection, and even genomic information analysis, in bioinformatics. The term is often associated to the terms dynamics, adaptive, interactive, on-line, or batch... The majority of the learning methods were initially defined in a non incremental way. However, in each familiy of these methods, were initiated incremental variants making it possible to take into account the temporal component of a data flow. In a more general way incremental clustering algorithms and novelty detection approaches are subjected to the following constraints: (1) Possibility to be applied without knowing as a preliminary all the data to be analyzed; (2) Taking into account of a new data must be carried out without making intensive use of the already considered data; (3) Result must but available after insertion of all new data and must not depend on the order of arrival of the data; (4) Potentia change in the data des_cription space must be taken into consideration.
Topics: Incremental techniques:
Novelty detection algorithms and techniques
Concept drift detection and management techniques
Incremental clustering methods (hierarchical, density-based, ...)
Adaptive neural methods and associated Hebbian learning techniques
Probabilistic approaches
Graph partitioning methods and incremental clustering approaches based on attributed graphs
Incremental clustering approaches based on swarm intelligence and genetic algorithms
Visualization methods for evolving data analysis results
Application domain:
Evolving textual information analysis
Genomics and DNA micro-array data analysis
Ambient intelligence and robotics
Industrial process management and control
Privacy, security and biometrics
Intrusion and anomaly detection
Adaptive recommendation and filtering systems
Supervision of communication networks
Energy management and planning