Learning in Non-Stationary Environments Methods and Applications

Prologue.- Part I: Dynamic Methods for Unsupervised Learning Problems.- Incremental Statistical Measures.- A Granular Description of Data: A Study in Evolvable Systems.- Incremental Spectral Clustering.- Part II: Dynamic Methods for Supervised Classification Problems.- Semi-Supervised Dynamic Fuzzy K-Nearest Neighbors.- Making Early Predictions of the Accuracy of Machine Learning Classifiers.- Incremental Classifier Fusion and its Applications in Industrial Monotiroing and Diagnostics.- Instance-Based Classification and Regression on Data Streams.- Part III: Dynamic Methods for Supervised Regression Problems.- Flexible Evolving Fuzzy Inference Systems from Data Streams (FLEXFIS++).- Sequential Adaptive Fuzzy Inference System for Function Approximation Problems.- Interval Approach for Evolving Granular System Modeling.- Part IV: Applications of Learning in Non-Stationary Environments.- Dynamic Learning in Multiple Time-Series in a Non-Stationary Environmenty.- Optimizing Feature Calculation in Adaptive Machine Vision Systems.- On-line Quality Contol with Flexible Evolving Fuzzy Systems.- Identification of a Class of Hybrid Dynamic Systems.