Basic data mining concepts – data representation and visualization. Classification techniques: decision trees, rule-based classifier, nearest-neighbor classifier, Bayesian classifier, artificial neural networks, support vector machines. Cluster analysis: density-based cluster, graph-based cluster. Basic learning mechanisms: supervised and unsupervised. Temporal and spatial mining: prediction, time-series, regression. Performance evaluation: ROC curves, confusion matrix. Applications of data mining: anomaly detection, remote sensing, bioinformatics and medical imaging. Programming exercises will be assigned.
Graduate and Doctoral Courses